A research engine, idea library, and strategy-building workspace rolled into one. Algo Vault is designed to help traders cut through the noise, find robust trading ideas faster, and move from research to implementation without drowning in academic papers, hype, or endless YouTube rabbit holes. Come and check it out!

Friends, I want to give you a slightly more personal update in this post. Yes I want to introduce you to Algo Vault, and yes I want to make sure that those who haven’t seen what’s inside the Algo Collective and Algo Academy get the scoop, but I also want to paint a picture of who I am and where I want to take this, so that I attract the best fitting collaborators. Essentially, I think that means I want to find people who can appreciate this is still early-days for me and have an interest in collaborating together over the long term. I know there’s a lot of competing noise out there, some of it from very bright individuals, but you know, it always comes back to this for me: do they actually trade successfully? Do they have the business head to separate academic theory from profit? Do they in fact want to develop meaningful connections and actually work together? These are my priorities, if you share them, we’d be a great fit. Thanks for all your support and feedback.

Ok, let’s talk about the newest addition for paid subs: Algo Vault.

What It Does

• Brings together hundreds of quantitative trading papers

• Turns complex research into practical, trader-focused summaries, including code in Python, Easy Language and Real Test

• Extracts the parts that actually matter for implementation and robustness

• Surfaces multiple strategy ideas from each paper, not just the headline concept

• Uses AI extensively to help us out, with API connections to all of the major models. Using AI like this is not cheap. You get the benefit.

What You Get

• Clear summaries focused on:

  • practical implementability

  • robustness of the idea

  • markets traded

  • data required

  • strategy style

  • indicators used

  • trade frequency

  • complexity

  • key risks to watch

• The essential strategy logic and the most important takeaways, without the fluff

Built for Action

• Key metrics extracted for fast evaluation

• Equity curves generated

• Basic code templates created so you can start building immediately

• Starting code templates delivered in:

  • Pseudo Code

  • Python

  • Easy Language

  • RealTest Script

Powered by Community

• Add comments, files, and improvements

• Uplift and enhance the base code together

• Upvote and downvote papers so the best ideas rise to the top

• Suggest new papers, magazine articles, and research ideas for inclusion

• Collaborate through discussion, research, and study groups inside the Algo Collective ecosystem

Why It Matters

• Saves enormous research time

• Helps you filter a curated universe of ideas quickly

• Lets you search for exactly what matters to you

• Makes it easier to move straight from idea to testing

• Anchors strategy development in academic rigour, while stripping out the fluff and hype

Powerful Search and Filtering

Filter on almost anything, (no more wading through papers blindly), including:

• strategy type

• market type

• timeframe and bar type

• keywords and concepts

• implementability

• publish date

• and so many more!

Plus you can favourite, vote and sort by what matters to you.

Watch the overview video, you’ll be impressed!

The Big Opportunity

No academic paper is perfect out of the box. But with a strong community and professional traders contributing, Algo Vault becomes a serious edge: a place to discover, refine, validate, and build robust strategies faster than you could on your own.

Become an Annual Member

Algo Vault is currently included free for Annual Members only — and this tool alone is worth the price of admission. Join now, get access while it’s still included, and help shape what could become one of the most valuable strategy research resources in the Collective. There will be a price tag on this soon, clearly it’s value will become enormous once as the library of validated and robust strategies grows. Who knows where we’ll take this? We’d love to have you build it out together with us.

Don’t forget that Algo Collective is already full of value, and I have to admit, probably best for the annual member. Why do I say that? Because I’m mindful of how much this is growing, and just how incredible this will be inside of 12 months. Those who see that are going to make invaluable collaborators, and by helping shape the future, will get the most targeted results. You’ll be patient with me as I build things out. Hopefully, you’ll see I’m here to actually help and I’m honestly interested in building relationships.

Traders in transition, looking to break through this year, jump on board.

Here’s a reminder of what’s going on inside already.

Algo Terminal is a few thousand lines of Python that fully automates your trading with IB. There are so many neat features. The community is working together to uplift it, making it capable of anything. It’s for members only and free for annual subscribers.

Python for Quants is a free course from Tom Starke. And there are more available inside if you want to continue the journey with him.

The Alpha Sessions are the weekly, live mentorship sessions with me. I sometimes bring along other faculty to do a joint workshop, for example, next week it’s with Laurens Bensdorp.

The Podcast Bonus Content is the 15 minutes I try and do with every guest after the show where I squeeze them to deliver some more private IP for the Collective.

There’s more: there’s the fact that it’s a true community space, where you can really interact with others and generate meaningful connections with other collaborators. Then there are other tools, workshops, and soon, more strategy ideas, code, and then…

Courses built for you. I’m working on aggregating the knowledge I have with all that I’ve gleaned from the network, and building out more and more fantastic, targeted courses. Of course, I’m actively working on the ‘coming soon’ courses from the other faculty. Yep, I’m busy! : )

Don’t forget the courses that are already live in Algo Academy.

Crypto Trader’s Edge is a comprehensive walkthrough of about 15 crypto strategies, using Trading View, and an incredible start for the newer systematic trader. It’s also of interest to the more experienced one, since the strategies are readily implementable.

Python for Quants is a series of 4 courses by Tom Starke that cover so many of the essentials for quants, without wasting time on anything you don’t need.

See you on the inside.

Simon

Subscribers get a community, bonus content, strategy library, mentorship & more.

3 Days Free

Samir’s Substack has some wonderful material, and today’s write up in inspired by his article “The Emperor Has No Alpha – What Data Mining Reveals About Academic Finance”. Forgive me for drawing heavily from it, but it’s great, and you should read it in full here:

Samir Varma

The Emperor Has No Alpha

A particle physicist’s take on why the peer review process might not be adding the value you think…

Read more

2 months ago · 18 likes · 4 comments · Samir Varma

In his article he references a paper from the Federal Reserve Board: “Does Peer-Reviewed Research Help Predict Stock Returns?”

The answer – “not really”. What a scientist like Samir reminds us of is that “elegant theories must predict, not just explain.”

In the Fed paper, 29,000 accounting ratios were brute-force data mined for statistical significance and compared to 212 peer-reviewed return predictors from academic studies. The result? Both approaches retained around 50% of their predictive power out of sample.

In physics, theory often leads the way. Scientists predict something should exist, then go looking for it. As Samir puts it, “Theory constrains the search space. It tells you where to look”.

Academic finance likes to imagine it works the same way.

A predictor is published. Then comes the explanatory framework. Maybe it works because investors are being compensated for risk. Maybe it works because of behavioral reasons. Maybe it reflects information asymmetry, attention effects, limits to arbitrage, or some other respectable academic mechanism. The theory is supposed to help us separate genuine phenomena from statistical rubbish.

But the Fed paper would suggest that theory does not seem to do that job very well.

That is the uncomfortable punchline. And for traders, it matters.

Categorizing by theoretical foundation: risk-based, mispricing-based, and agnostic, the paper found that the only category showing any real sign of outperformance is the agnostic research: the papers that refuse to take a theoretical stance.

That is a serious result. It suggests that, in markets, elegant explanations may be far less useful than people think. Worse, they may create a false sense of confidence. How many of them are created to sell a hedge fund?

Oh, and the other theory that did actually out-perform? Momentum!

Data Mining Is Not the Villain

In quant circles, “data mining” is often used as shorthand for bad research. Overfitting. Curve-fitting. Random pattern hunting. Statistical hallucination dressed up as alpha. Fair enough. Bad data mining exists. Plenty of it. Most of it ends badly.

But the deeper point is this: all empirical research is, at some level, data mining. The real issue is not whether you search the data. The issue is whether you search it with rigor.

If useful information exists in prices, accounting data, flows, or market structure, a computer can help uncover it. This shouldn’t a surprise. You do not need a grand theory before you are allowed to notice that a pattern is there. The market leaves fingerprints. Some are noise. Some are not. Your job is to figure out which is which.

In his paper Samir argues that data mining could have uncovered many of the major themes in asset pricing before they were formally published. Investment, accruals, external financing, earnings surprise—many of these broad areas could have been identified by searching the data first, with theory arriving later as explanation rather than discovery.

That should change how a trader thinks.

It means the academic paper is not always the origin of insight. Often it is the formalisation of something the data was already trying to say. The theory may tidy it up, give it a name, and provide a narrative respectable enough for publication. But the pattern itself may have been available long before the journal article arrived wearing a tie.

That is not an argument against academia. It is an argument against passivity.

If a trader waits for peer-reviewed permission to investigate an idea, he may already be late.

Academic Research Still Matters

Now, let us be clear. None of this means academic finance is useless. It’s incredibly helpful. Samir mentioned to me he has probably read 3 papers a day for many years.

The academic literature remains essential because it gives traders a map of what has been observed, what has been tested, and how others have tried to explain recurring effects. It gives you language, structure, categories, and a body of work to interrogate. It tells you what others think they have found. And often, that is enormously valuable.

Now, if only you had a tool to accumulate hundreds of great academic papers into a searchable library, summarise their trading potential, produce the strategy code even, and quickly test them before proceeding with deeper research? What if you could work collectively with others testing, sifting, letting the best ideas rise to the top? Funny, I had the same thought, and this is why I’m about to drop the Algo Vault for Collective annual subscribers. It’s exactly that.

Samir, like any good scientists reveals the crucial shift we need to make in our approach to these theories: once you understand what the academics are saying, your job is not merely to admire it. Your job is to figure out “why they’re wrong”.

That is where the trader’s work begins.

Not because academics are fools - often they are very smart. But because they are playing a different game. They are trying to explain patterns in a publishable framework. You are trying to make money going forward, after costs, after slippage, after crowding, after decay, and after your own psychology starts whispering that this time it is different.

Those are very different objectives.

Stand on the shoulders of giants, but you better believe you need to ‘get to work’ yourself.

An academic explanation may be directionally useful and still be wrong in the ways that matter most to a live trader. The risk framework may miss the actual driver. The behavioral story may be too neat. The statistical result may weaken after publication. The implementation assumptions may be unrealistic. Or the entire thing may only survive in sample because of specification choices no practitioner would ever use in live trading.

That is why understanding the literature is necessary but not sufficient. You must know the “what.” Then you must attack the “why.”

Why should this persist?
Why did it work?
Why did it stop working?
Why did the paper measure it this way?
Why would a live trader actually get paid for bearing this exposure?
Why would this effect survive after being published, copied, and crowded?

That line of questioning is where genuine edge begins.

Now, even by answering the ‘why’, we may not need an elegant theory, we just nee to have tested it till we threw up, so that the ‘why’ is ingrained so deeply in us that we are comfortable we can trade it. The Agnostic / ‘unexplainable’ theories can have a ‘why’ that lives precisely in the fact that they ‘don’t fit neatly’ with academic theories.

Samir quotes Peter Brown, co-CEO of Renaissance Technologies, said in Gregory Zuckerman’s The Man Who Solved the Market:

It’s a quote I’m happy to repeat. Samir adds “The patterns that persist are precisely the ones that resist explanation.”

PS: Don’t forget we interviewed Zuckerman way back when:

That is the point, isn’t it?

The signals that are easiest to explain are also the easiest to crowd. The ones that fit neatly into an academic model are the ones most vulnerable to being noticed, packaged, published, marketed, and arbitraged to death. By the time a signal becomes intellectually elegant, it may already be commercially extinct.

Meanwhile, perhaps the weird stuff survives longer precisely because it resists neat explanation. The pattern looks uncomfortable. The rationale is murky. The narrative is weak. Which means fewer people pile in with conviction, fewer funds leverage it aggressively, and fewer allocators convince themselves it is a durable gift from the heavens.

Ugly signals may live longer because they do not flatter the human need for coherence.

But hey, this is just my theory, you should test it. It probably doesn’t hold up.

Theory Does Not Trade for A Living. Process Does.

The real lesson here is not that theory is worthless. It is that theory is not a substitute for research discipline.

What actually seems to predict persistence is not theoretical elegance but statistical strength. The stronger the in-sample evidence, the better the odds that something real is there.

That is why the serious quant has to be maniacal about process.

In fact, one advantage of looking at older papers, is that there is more out of sample time for you to check them against. This is a common issue with the peer review process; it doesn’t generally do robustness testing out of sample.

You need to test ideas hard. Across time. Across markets. Across parameter ranges. Across regimes. Before publication and after publication if possible. Before costs and after costs. Under realistic assumptions, not fantasy ones. You need to know what breaks the idea, what strengthens it, what dilutes it, and what its true behavioural profile looks like when the equity curve gets ugly.

That is where conviction comes from.

Papers are full of great ideas, plausible explanations for phenomena are important, but conviction comes from doing the work yourself and understanding what the work is actually telling you.

This is especially important because many traders do not really understand the ideas they trade. They understand the headline. They understand the sales pitch. They may even understand the backtest summary. But they do not understand the mechanism well enough to survive the periods when the strategy inevitably disappoints.

That is fatal.

If you do not understand the strategy deeply, you will not trust it when you most need to. And if you do not trust it, you will override it, reduce it, abandon it, or morph it into something else at exactly the wrong moment.

Your Edge Must Fit You

The final filter is not just whether a signal is statistically valid. It is whether it is congruent with the person trading it.

Samir says “that durable competitive advantage needs to be 100% congruent with your own personality”.

That line is more important than most people realise.

A strategy is not just a return stream. It is an experience. It has a rhythm, a temperament, a pattern of pain. Some strategies win infrequently but explosively. Some grind steadily then suffer sharp reversals. Some require patience bordering on monasticism. Others demand speed, decisiveness, and emotional resilience in the face of constant noise.

If the strategy clashes with your nature, it will eventually beat you, even if the backtest is valid.

A risk-averse person may not be able to hold a sharp momentum system through its inevitable drawdowns. A slow, patient thinker may sabotage a short-term strategy by second-guessing constant signals. A trader who craves narrative certainty may abandon a robust but ugly model simply because he cannot explain it elegantly enough to himself.

That is why your edge cannot be borrowed. It cannot just be copied from a paper, a fund manager, or a clever person on the internet. Samir says it so well, “Your edge must be yours. Not borrowed. Not copied. Not theoretically optimal for some abstract investor. Yours”.

That does not mean inventing something from nothing. It means making it your own through understanding, research, and repeated testing until the logic and the pain profile are both something you can actually live with.

The Trader’s Real Job – Practical Take-Aways

I’ve said it before – Trading is a business. Writing academic papers is not. Academic insight remains essential because it tells you what has been seen and how people have framed it.
But your real job is to test it yourself, understand it deeply, and figure out where the academic story is incomplete, fragile, or simply wrong.

That is where edge lives.

Not in theory alone.
Not in data alone.
In the disciplined confrontation between the two.

And then, one level deeper still, in building something you can actually trade.

Because in the end, the best strategy in the world is useless if you do not understand it, do not trust it, or cannot execute it.

That is why the work matters. Test it. Break it. Rebuild it. Strip it back. Understand it until it is no longer just an idea from a paper, but a method you could hold through stress. Empirical evidence is your only friend. Here’s the only ‘process’ you really need: test until you throw up, then test some more.

One last quote from Samir. “The data mining result in this paper is liberating in this sense. It means you don’t need to genuflect before academic authority. You need to understand the academics, yes. But then you need to find what works for you, validated by data, congruent with your psychology.

That’s a much harder problem than reading papers. It’s also the only problem that matters.”

Research widely, always be skeptical, don’t assume complexity makes more money, mine the data vigorously, and, if it holds statistical significance out of sample, then devise the theory.

Get in Touch with Samir

Personal Website

Fund Website

His Book

On X

Substack

And in his extended conversations with me he mentioned the groundbreaking work of his colleagues in quantum mechanics, you may want to check that out.

The Weight of Quantum

If you loved Asimov and want to read about how the three laws of robotics were developed after his death, check out Roger MacBride Allen, who wrote three novels (Caliban, Inferno, Utopia), approved by Asimov shortly before his death, exploring the creation of “No Law Robots” and “New Law Robots” — a direct interrogation of what happens when the Three Laws framework is dismantled or reformed.

Samir recommended this book as an excellent introduction into quantum physics:

Waves on an Impossible Sea by Matt Strassler

I threw his white paper into NotebookLM for a wonderful summary, and thought I’d share it. Let me know if you have any questions for Samir, and of course, I’ll be deep-diving with him in the Members Only area, in the Collective.

Like Schrödinger’s cat, your backtest is both profitable and worthless—until you open the box with real capital… and the market decides which one it is. ; )

The Collective

Crypto might attract the same kind of attention a chainsaw gets at a dinner party, frequently handled by people who should not be touching it.

That is exactly why it remains so attractive to systematic traders.

The usual retail approach to crypto is painfully predictable: find a coin, fall in love with a narrative, survive one big run-up, then give it all back when the market decides to impersonate gravity. The smarter (systematic) approach is very different. You do not build a crypto portfolio by finding “the next Solana.” You build it by creating a process that can survive crypto’s violence while still harvesting its upside, and volatility.

Many quant traders have shied away from Crypto: it’s hard, immature, structurally messy, and has limited data history. But if you think like a trader, you’ll want to go to where the easy money is. The question is, can it be done without over-fitting, given the history is short, and full of insane rides that will likely never happen again. Can we navigate the pump and dumps, the meme coins, the counterparty risk, the 24/7/365 trading without crazy risks? David Bush (like Pavel on the pod before him) answer with a resounding: ‘of course’.

One of the best rules anybody can learn about investing is to do nothing, absolutely nothing, unless there is something to do... I just wait until there is money lying in the corner, and all I have to do is go over there and pick it up... I wait for a situation that is like the proverbial “shooting fish in a barrel.” Jim Rogers (in ‘Market Wizards’)

New Market, New Thinking

David highlights the obvious but not so obvious: crypto trades 24/7/365. That means far more time for price discovery, more volatility, more dislocations, and more opportunities for systematic traders willing to treat it as a live laboratory rather than a religion. The volatility is not outsized compared to equities if adjusted for this enormous leap in time that the market’s are open for price discovery.

The second mindset shift: simple logic beats fancy nonsense

Crypto’s complexity and modernity don’t mean the solution is to become even more complex. It’s the opposite. New markets have the same profile they always did - speculation dominates; rules and regulations are lax; institutional adoption is less. This means less efficiency and more edges, if you’re willing to participate on the path to ‘full maturity’.

Both David and Pavel remind us that Crypto has limited reliable history. Bitcoin data is short. Altcoin data is much shorter. That means you do not have the luxury of building overengineered models with twenty moving parts and a machine-learning cherry on top. If you do, you are not finding truth. You are decorating noise.

David’s preference is classic logic: trend following, momentum, mean reversion, breakouts, volatility-aware exits, and simple filters that generalize well. He repeatedly stresses the need to use principles proven in other markets, then adapt them carefully to crypto.

Start with ideas that already work in other asset classes, then make as few changes as possible when bringing them into crypto. The main adjustment tends to be in the exits, because crypto is faster, noisier, and more explosive than stocks or commodities.

So the working rule is simple:

• Start with robust ideas, not clever code.

• Use as few conditions as possible.

• Make crypto-specific adjustments where the market genuinely demands them.

• Treat complexity like a tax, because that is exactly what it is.

Then there’s the bonus data:

Crypto has new data, additional opportunities. There’s ‘on-chain’ data for starters, but there are indexes and metrics that are only available to crypto traders and can definitely be used for filters and regime switches. Add this to your OHLCV data for extra risk management, and extra spice.

And we like a clean build-process that is ‘research driven’

Build edges first, strategies second, portfolios third.

Most traders want a “strategy” immediately. That is understandable. It is also backwards. First identify statistically meaningful edges or alpha engines, then derive strategies from them, and only then combine those strategies into a portfolio.

We’ve been talking about this in the Collective. How to build a ‘research first’ pipeline for ‘robust strategy creation’. Truly fascinating discussions with some legendary traders. It’s all Members only content, but super value:

Sign up here: collective.algoadvantage.io

That means looking under the hood. Trade-level analysis matters. You want to know what each edge actually does. When does it win? When does it fail? Does it work because it captures one or two freak trades, or because there is something real under the surface?

David makes a particularly useful point here for crypto: in trend-following systems, average trade can be misleading because a few outliers can drag the average upward. YES, this is normal for trend following, BUT with Crypto these moves can be so over-sized you don’t want that level of optimism going forward! David looks at median trade data. If the median trade is pathetic, the edge may not be robust beneath the glamorous surface. That is a nasty but necessary test.

Trend following and mean reversion: use both

Trend following

Trend following is the obvious fit for crypto because crypto occasionally goes berserk in your favour. These are the escape-velocity trades David talks about: lower hit rate, bigger payoff, positive skew, and the need to let winners run. That means breakouts, momentum, and trailing exits matter more than pretty win rates.

Pavel agrees, but adds an important twist: in crypto, long-term momentum exists, but often in shorter windows than traders expect. Crypto trends fast, overshoots fast, and then turns into a drunken crab. So even the “long-term” momentum trader in crypto may be operating on much shorter holding periods than an equities trader would assume.

Mean reversion

Mean reversion matters too, especially on the long side. Crypto is often a “mean-reversion-long” market in the sense that sharp selloffs frequently bounce. That makes dip-buying logic, quick profit-taking, and higher win-rate systems highly relevant. But mean reversion brings its own ugliness: negative skew, left-tail risk, and the constant temptation to keep averaging into stupidity.

Why the mix matters

The real magic is not “trend following versus mean reversion.” It is the combination.

Short-term mean reversion short strategies can help reduce the open exposure created by momentum long systems when markets become overheated. Meanwhile, mean reversion long strategies can help offset the drag from momentum short models in a market that tends to snap back upward. In other words, the styles can hedge one another if combined intelligently.

That is a serious portfolio insight. A good crypto portfolio is not just a bunch of profitable strategies dumped into a bucket. It is a set of return streams that interact in useful ways when the market gets ugly.

Universe selection: careful what you test

Crypto has a survivorship bias problem the size of a small planet.

If you only test today’s winners, you are effectively asking history to flatter you. David is explicit on this point. In his altcoin research, he did not simply take the current top names and pretend that was a historically honest universe. Instead, he wanted coins with enough data from around 2020 onward, then ranked or grouped them with market cap as a secondary filter, not the only one.

The additional solution is to trade a full portfolio with survivorship bias free data (include dead coins) and trade the ‘top 20’ or ‘top 50’ by, say, turnover. Even then, different exchanges have different coins and different liquidity. The serious trader might revert to coin market cap historical data, and I’ll soon share how to do that using their API & Python.

Pavel makes the same point from the institutional side. He warns against building models on a few coins that happened to perform spectacularly in hindsight. His preference is always a portfolio approach across a tradeable universe, not a hero trade approach based on yesterday’s poster child.

Robustness in crypto is not optional

If there was one theme louder than the rest, it was robustness.

David repeatedly argues that out-of-sample data must be treated like a synthetic live environment. If a model fails there, you do not tweak it and pretend nothing happened. You accept that the development process failed and move on. Painful? Yes. Necessary? Absolutely.

This can be extended into a much broader framework. Robustness is not just about the model. It is about the portfolio, the data, and the infrastructure:

• using simple, causal logic

• testing alternative daily closes and offsets

• making sure models work across a broad universe

• monitoring whether each model behaves as it should in the regime it was built for

The main point is that ‘robustness testing’ in crypto can’t rely on the same tools one might use in markets with decades of mature history. Hence the need to lean on simple, causal logic for time-tested models and principles.

Risk management: the portfolio is the real stop-loss

Hard stops are often a poor primary risk tool in crypto because intraday volatility is savage and false breakouts are common. The preferred approach is broader: small position sizing, many models, many positions, regime-aware exposures, and explicit hedging structures inside the portfolio.

David mentioned using Monte Carlo testing as a precursor to sizing because it shows alternative trade histories and helps define what kind of drawdown you actually might have to live through.

A high-performance crypto portfolio manages risk through structure more than prediction.

That means:

• many small positions rather than a few oversized bets

• multiple strategy types rather than one style

• liquid, tradeable coins rather than random carnival tokens

• regime filters and hedges rather than faith

• exchange diversification rather than custodial complacency

And yes, exchange risk matters. Both David and Pavel discuss it directly. Spread capital across multiple exchanges. Keep only what you need on-exchange where possible. Understand custody risk. Crypto is one of the few places where your strategy can be right and your venue can still mug you in the parking lot.

The all-weather portfolio is the end game

The ‘all-weather’ blueprint in a world of ‘loose pants’ (not over-fitting in the slightest) is combining momentum and mean reversion, long and short, aggressive and regime-dependent models, in ways that keep the portfolio exposed to opportunity while muting left-tail damage.

Build a library of functional components and then combine them at the portfolio level, where correlation, diversification, sizing, and risk-adjusted returns really start to matter. Individual strategies are not the final product. They are ingredients.

That is how you should think about your portfolio too. As a collection of behaviours.

Some models catch breakouts. Some fade overstretched moves. Some hedge. Some only wake up in hostile regimes. Some exist mainly to improve the portfolio rather than to look brilliant on their own.

Conclusion: build something that deserves to survive

If you want a practical takeaway, here it is.

A high-performance crypto trading portfolio is built on a few blunt truths:

• Crypto is still rife with inefficiency – retail trading creates opportunities.

• Simplicity beats cleverness when the data history is short.

• Classic logic usually travels better than bespoke wizardry.

• Trend following and mean reversion both matter; together they matter more.

• Robustness must come from elegant simplicity and not from complexity.

• Risk management lives at the portfolio level, not just at the stop-loss line.

• Diversification across models, coins, regimes, and exchanges is what keeps you alive.

Again, there’s a free Masterclass with David in the Collective.

Trade well and prosper!

Simon

Connect with David:

Substack

Website

X

Linked In

His Crypto Course

We don’t want you picking up pennies in front of steam rollers.

First, Algo Collective (our members area) and Algo Academy (our course platform hosting courses from market wizards) are now OPEN! Check it out on the website. I’m pretty excited about this step: the Collective is already buzzing and courses from Tom Starke (Python for Quants) and David Bush (Crypto Trader’s Edge) are ready to go. The Founding Member discounted deal is only THREE spots away from being full (only took a day!), and you can jump in for a free two-week trial. See you inside my friends (over 30 mins of extra deep dive with Michael).

If you’ve ever blown up a trading account or sat through a gut‑churning drawdown, you already know why position sizing isn’t just an academic exercise. It’s the lever that controls how much capital is exposed on every trade, and therefore how likely you are to survive long enough to let your edge play out. Good sizing techniques limit losses to a tolerable fraction of your capital and can reduce the stress of trading. Good traders often risk no more than 1–2 % of their account on any single trade; this modest risk per trade means even a string of ten losses only knocks the account down by ~20 %, leaving plenty of room to recover.

But there’s a paradox. The math tells us we could stake more when the edge is good – the Kelly criterion, for example, may suggest risking 20 % when win–loss ratios are favourable. Real markets, however, rarely deliver independent outcomes with fixed win rates or identical loss sizes. Slippage, gap risk and regime changes can turn theoretical optimums into account killers. Survival trumps theory.

In this primer we’ll lay out the common position sizing methods, comment on how different types of traders (futures vs. stock, short‑term vs. long‑term) use them, and share a simple mental framework for thinking about sizing from a risk and statistical perspective. Throughout we’ll lean on the mathematics of the Kelly criterion and its cousins – but we’ll also recognise the messy reality of actual trading which can only be seen by careful back-testing or live trading experience. My conclusion is that the goal is necessarily to optimise every cent of expected return but to stay in the game long enough to compound whatever edge you have. Survivors can compound wealth, the other 90% become cautionary tales that don’t get told.

Let’s start with the basics.

Overview of Position Sizing Methods

I’m going to break the concept of position sizing into two groups and present them in two tables (non-exhaustive). These tables separate initial trade‑sizing techniques—methods that determine how much to risk on the first entry—from dynamic scaling rules, which adjust position sizes as trades evolve, account equity changes or market regimes shift.

I’m not smart enough to work out how to insert a table into Substack, so the following is a list of sizing techniques with their Method, Key Idea & Usage / Implementation:

Fixed percentage risk (Fixed fractional)

Risk a constant percentage of account equity on each trade; size = (account × risk %) ÷ (stop-loss distance).

Typical example is to risk 1-2% of your account on each and every trade.

Can be implemented on stocks or futures. Generally, requires measuring the volatility (usually an ATR) of the contract, and setting a stop based on that volatility. A highly volatile stock will need to be given more room to move, and thus a smaller percentage of the account can be allocated to the trade so that the total loss on this trade is the equivalent to the loss on any other trade.

Very much the focus for trend followers who want to be as ‘non-predictive’ about the future as possible. Since the future is unknown, assign the same odds to every trade and wait for the outliers to carry you home. Already we can see that the emphasis is on managing your capital to survive, rather than trying to ‘read the market’ and ‘predict the odds on this trade’.

Suitable for stocks, forex and futures. This method normalises risk across instruments and market regimes by adjusting the position when ATR changes.

On the downside, you may have a data-driven reason that you feels provides compelling evidence that ‘some trades are better than others’ and are worth putting the pedal to the metal on.

Fixed fractional/Equity-based

Allocate a fixed fraction of total capital to each position (e.g., 5 % of account) regardless of stop distance.

Suitable for portfolios of stocks or ETFs. Amount invested per position remains constant as capital changes. Stops are secondary and would add an additional layer of thought.

The advantage of simplicity, and if it tests out that simple is as good as complex, go with simple.

Fixed contract size

Trade a predetermined number of shares/contracts; risk varies with price and stop distance.

Common in futures or when trading lots. A trader might always buy 1 contract or 100 shares; the monetary risk changes with stop-loss size and volatility.

Frequently an artifact of the fact that smaller account holders can’t trade less than 1 futures contract, since the contract values are so large. This generally means it’s a sub-optimal approach, but you have to work with what you have.

Common in prop shops and very short-term trading where other risk controls dominate.

Leverage-based

Size positions to maintain a target leverage ratio (e.g., 5:1).

Used in margin trading or leveraged futures; position size = (account × target leverage) ÷ price.

Just a variant of equity based really, beefing it up.

Kelly criterion / Optimal f

Use win rate and average win/loss to calculate the “optimal” fraction of capital to risk using the precisely optimised formula.

Academic method; maximises expected growth but can produce high drawdowns. Many traders use a fraction (e.g., half-Kelly) to reduce volatility.

Produces outstanding returns in theory (because it’s literally the mathematical optimum), opens up risks if reality doesn’t line up with the textbook.

Risk parity / Equal risk contribution

Allocate capital based on risk, not dollar amounts; each asset contributes equally to portfolio volatility.

Used by portfolio managers across asset classes. Weights are inversely proportional to each asset’s volatility and rebalanced periodically to maintain equal risk.

Usually, the idea is to maintain a certain overall volatility for the portfolio, and that (rather than strict profitability), becomes the focus. Think institutional fund manager.

Equal dollar weighting

Invest identical dollar amounts in each instrument.

Simple to implement for stock portfolios; makes rebalancing mechanical but may overweight smaller, more volatile names.

Sort of the stock equivalent of ‘fixed contract size’ for futures. Stocks don’t have the same limitation of futures however (since they are quite divisible) so, I’m not sure why you’d bother with this. Nevertheless, you often hear about it on the web.

Value-at-Risk (VaR) sizing

Limit positions so that the calculated VaR per trade or portfolio stays under a specified threshold. Used by institutional funds. Requires models of historical or parametric Value at Risk (think, ‘how much could I lose under a worst-case scenario); translates allowed loss into number of shares / contracts.

CPPI (Constant-Proportion Portfolio Insurance)

Maintain a floor (safe asset) and invest a multiple of the cushion (equity above the floor) in risky assets. Popular in asset-allocation strategies. When equity rises, the risky allocation increases; when markets fall, exposure shrinks to protect the floor.

Maximum drawdown control

Cap position size so that a worst-case losing streak cannot exceed a predetermined drawdown threshold.

Translate the allowable drawdown into a per-trade or per-day size cap; popular among hedge-fund managers and systematic traders to avoid “risk of ruin”.

Now we are thinking ‘real world’ rather than ‘expected probability’.

This is definitely not an exact science, but now I’ll try and define position sizing concepts that pertain more to “how position sizing might change over time” (dynamic) as opposed to how to set “initial size”.

Again, the below covers Method / Key idea / Usage / Implementation

Martingale

Double position size after each loss to recover previous losses.

High-risk approach sometimes used in gambling or small-stake strategies; increases tail-risk dramatically and can lead to catastrophic drawdowns. Most professional traders avoid it.

Anti-martingale (reverse martingale)

Increase size after a winning trade and reduce it after a loss.

Emphasises capital preservation. The trader uses profits to fund larger positions and resets to baseline risk after any loss. Suitable for trend-following strategies where long winning streaks can be exploited.

Pyramiding

Add to winning positions in increments; never add to losers. Start small (e.g., 1–2 % of capital) and add only when the trade moves in your favour, moving the stop to lock in gains.

Used by swing and futures traders. Helps compound gains in strong trends while keeping initial risk small. Requires clear rules for profit milestones and stop adjustments.

Equity-curve scaling

Adjust position size according to your trading equity curve: increase size when the equity curve shows statistically significant improvement and cut size when the curve weakens.

Turns the equity curve into a “governor” for sizing. Useful for systematic traders to capitalise on hot streaks and reduce risk during drawdowns.

Generally, every trader wants to scale as their account size scales in one form or another to maximise compounding. This can be more or less aggressive (e.g. you could measure your account size daily and change sizes accordingly, or you could size every trade the same for the whole year, see where you’re at come year end, and decide how much to increase your sizing then).

Dynamic volatility / edge / risk-adjusted sizing

Dynamically shrink positions when market volatility rises and expand when it falls; size trades based on setup quality (edge) and portfolio correlation.

Institutional desks might adjust position size according to ATR or VIX thresholds and stop distance. They might also cut size after equity drawdowns or sequences of losses, and cap exposures when correlations cluster.

Drawdown-based scaling

Reduce position size after a series of losses or when account equity drops by a set percentage; resume normal sizing only after equity recovers.

Helps traders survive losing streaks by preserving capital; widely used by discretionary and algorithmic traders to maintain psychological stability.

Equity-adjusted percentage risk

Recompute position size daily or after each trade based on current account equity; positions naturally grow or shrink as the account grows or declines.

Common for stocks and futures; automatically scales risk without changing the percentage; sometimes combined with pyramiding to increase size after winners.

A method of equity-curve scaling if you like.

Constant leverage rebalancing

Maintain a fixed leverage ratio by periodically rebalancing exposure; when equity grows, borrow more to maintain the ratio; when equity falls, reduce borrowed exposure.

Used by leveraged ETFs and futures funds; ensures constant volatility but requires strict margin monitoring to avoid forced liquidation.

Equal-risk contribution rebalancing (ERC)

Continuously rebalance so each asset’s marginal risk contribution stays equal.

In multi-asset portfolios, position sizes adjust as volatilities and correlations change. Similar to risk parity but applied dynamically to maintain equal risk contributions over time.

As an example, a winning trade which is becoming a massive outlier in your portfolio (perhaps making your whole year), will have its size reduced (reducing your profit if it continues its run) for fear of increasing the volatility of your portfolio.

Lessons from the Academics: Martingale and Kelly Math

There’s a seductive appeal and yet hidden dangers of Martingale and Kelly sizing. In a toy example with a $100,000 account risking $1,000 per trade and a 60% win-rate, a pure Martingale strategy (doubling after each loss) can absorb at most six consecutive losses before the required next bet exceeds the remaining capital (the drawdown would be $63,000, leaving only $37,000 to attempt a $64,000 bet). The probability of six losses in a row in a 60/40 game is 0.4096 %, but over hundreds of trades the chance of encountering such a streak approaches certainty (ask GPT for the math). The P&L distribution becomes highly negatively skewed: many small gains and an occasional blow‑up.

So, even if your strategy is genuinely 60% winners, the probability you avoid a 6-loss streak over many cycles goes to zero. If you trade enough, you will eventually experience the exact loss pattern the Martingale cannot fund. Basically, you can only keep doubling while you can still fund the next bet. This is the market’s ‘table limit’.

To make it concrete, the expected number of 6-loss streaks:

For 100 trades:

• N=100: (95)(0.004096) ≈ 0.39 expected streaks

For 1000 trades:

• N=1000: (995)(0.004096) ≈ 4.07 expected streaks

So in 1,000 trades, you shouldn’t be asking “will it happen?” but “how many times?”

Let’s ask it this way, what’s the probability of at least one 6-loss streak?

A decent back-of-the-envelope is Poisson: P(≥1)≈1-e^(-(N-5)q^6 )

• N=100: 1-e^(-0.389) ≈ 32%

• N=1000: 1-e^(-4.07) ≈ 98%

Different approximations vary a bit, but the conclusion is stable:

Over a long enough sequence, the catastrophic streak is not a “risk.” It’s an appointment.

Looking at Kelly, in an even‑money 60% win‑rate scenario, full Kelly suggests risking 20% of the account per trade. A single loss drops equity by 20%, five losses by roughly 67%. Under realistic conditions – slippage, gaps, non‑stationary edges and clustered losses – such aggressive sizing is suicidal. Fractional Kelly (half, quarter or even one‑tenth) is more prudent.

Alternatively, you can pick a fixed risk per trade (1–2 %) and ask, “how many consecutive losses can I survive before my account hits my maximum drawdown?”. With a 2.5 % risk per trade, 20 losses reduce the account by about 40%. If you can handle that psychologically and financially, that risk level is acceptable; if not, size down.

Enter Real Life – Markets are Full of Noise

Secondary risks (the stuff that kills real traders, not textbook traders)

Martingale math assumes a toy world. Trading is not a toy world.

1) Win rate is not constant

Your 60% is an estimate or an average over time. It says nothing about the path of those statistics in the short term. Regimes change. Execution changes. Slippage changes.

If the true win rate drops even a bit, the tail risk spikes.

Example: if win rate is 55% ⇒ q=0.45

0.45^6=0.0083

That’s about double the blow-up probability per cycle, from ~1/244 to ~1/120.

2) Loss sizes aren’t identical

Martingale assumes each loss is exactly “-$risk.”
Real trades have:

• gaps

• partial fills

• slippage

• volatility clustering

So the “6 losses = $63k” can become “6 losses = $80k” faster than you can say “liquidity”.

3) Risk-of-ruin is replaced by “risk of irrecoverable drawdown”

Even if you “survive” at $37k, you’re in a crater:

• You cannot continue the Martingale.

• Your required return to get back to $100k is: 100k/37k-1 ≈ 170%

That’s not “a setback.” That’s a new career.

4) Psychological liquidation

A 63% drawdown is where humans start inventing new religions.

Most traders:

• shut it down,

• change rules mid-stream,

• or revenge trade.

So the effective risk is worse than the math.

The core takeaway

A Martingale paired with a positive edge does not eliminate risk—it concentrates it into rare, catastrophic outcomes.

But… Surely We Can We Capitalize on Probabilities?

Sure, people do it.

First, you have to have a very strong risk framework. You had better know when it’s time to pick up your chips and walk away.

Second, you have to have a data-driven reason for assigning different probabilities to different trades. Now, I don’t think this is unreasonable at all. Most traders would agree long trades are less profitable in bear markets than in bull markets. Listening to Michael in this interview tells me he’s done an extraordinary amount of work on these two points. Prop traders and many discretionary traders also behave exactly the same way. They press hard into ‘A-grade’ trades, and fall back after a series of losses, or happily stand aside when conditions are not suited to their trading style.

In order to keep it short, I’ll reserve for members inside the Algo Collective the 30-minute deep-dive I did with Michael to really get into the rules of his strategies. I’m also happy to chat about the differences for futures versus stock traders, longer-term versus shorter-term, etc.

So, what’s my perspective?

Forget the academics, forge a path for survival, bring risk of ruin to zero, build additional skills over time. Stay in the game to compound your edge.

A Practical Framework for Sizing

Thinking about position sizing requires balancing three competing forces:

1. Mathematical optimality (Kelly) – The Kelly criterion maximises the expected rate of growth but is highly sensitive to estimation errors and assumes independent, identically distributed outcomes. Use it as an upper bound for how aggressive you can be. For example, if your backtest suggests a Kelly fraction of 20%, you might cap your risk at one‑eighth of that (~2.5%) to allow for estimation error and regime changes.

2. Drawdown survival (streak‑based) – Decide how big a drawdown you can stomach. If a 40% drawdown would force you to quit or drastically change your strategy, calculate the position size that makes a 20‑loss streak produce no more than 40% damage. This implicitly sets your risk per trade and provides a psychological anchor. In futures, you can translate a 1% risk into a number of contracts; in stocks, you can determine how many shares that risk represents given your stop distance.

3. Take a portfolio-based approach – the more strategies across the more markets you trade, naturally reduces bet sizes on each contract and on each strategy. You maximise your real-world capability of survival by diversification and trading an ensemble of strategies.

4. Real‑world noise – Win rates and payoffs drift, trades are correlated, and losses cluster. Add a safety factor by sizing for the worst plausible regime, not the average one. That might mean using fractional Kelly on pessimistic estimates of win rate and payoff, or sticking to a fixed percentage regardless of perceived edge. Keep an eye on volatility – if the market becomes wild, reduce size even further.

Survive First, Thrive Later

Position sizing is not about finding the magic number that maximises every theoretical dollar. It’s about staying alive. If you blow up your account, no future edge can save you. When evaluating any sizing rule:

• Run back‑tests or Monte Carlo simulations on your strategy, focusing on worst‑case losing streaks and drawdown depth, not just average returns.

• Account for slippage, gaps, changing win rates and fat tails. Rus stress tests and you’ll see how small deviations in win rate can dramatically increase blow‑up risk for both Martingale and Kelly strategies.

• Choose a sizing rule appropriate for your instrument. Futures traders should consider contract specifications and margin; stock traders should consider gap risk and diversification; long‑term investors might emphasise risk parity or equal weight; high‑frequency traders might lean towards very small fixed percentages.

• Be consistent. Constantly switching sizing methods because of emotions or recent results undermines the statistical edge of any strategy.

Above all, remember: your trading career is a marathon, not a sprint. Reality rarely matches the neat curves of a spreadsheet. “Optimal” f derived from a formula means nothing if you’re forced out of the game by a nasty losing streak or a market regime change. Know the math – it will inform your intuition and give you upper bounds. But then size so that you can survive the worst‑case scenarios, because only those who stay in the game long enough can compound their gains and eventually thrive.

Here’s to thriving!

Simon

Get in Touch with Michael

Website

Facebook

Robbins World Cup Advisors

There’s a new pod just about to drop, but meanwhile, there’s some BIG news.

Finally Launching Algo Collective & Algo Academy

Algo Collective is the private members area, but it’s not through Substack (I’ve got way too much going on inside) so you’ll need to visit the website to learn more. From extra podcast content; weekly workshops with myself (live); strategy development content; Python classes with Tom Starke; open Python code for an IB Order Management System; a forum filled with pro traders; and so much more, this is THE place to level up your systematic trading and connect with like minded individuals.

Check out what I’ve got going on here, I think you’ll find it pretty unique.

Take me to the Algo Collective!

Founding members are getting in cheap! AND you get 30% off your first course if you go with the Annual subscription. I’m capping that out quite soon but eveyone has to launch with a discount, so, jump in quick to take advantage of that! : )

Algo Academy is the platform for courses by genuine fund managers and market wizards. We’ve got (AAAQuants) with ‘Python for Quants’ courses and the illustrious David Bush from has been working closely with me to produce a powerhouse course we’ve called Crypto Trader’s Edge. I’m talking around 10 hours of video; over 430 slides; TradingView code; RealTest code; strategies for BTC and Alts; alternative data; smart crypto-specific regime awareness and so much more.

If you are newer to crypto or systematic trading, this is a ‘full lifecycle’ development path! But irrespective of your level, these trading edges are worth every cent, and I’m now building out my own diversified crypto portfolio with them!

It’s LIMITED TO 50 SPACES in this cohort so we can take care of everyone, and build out strategies meaningfully with them in the community area. Contact me through the website with any questions whatsoever.

Check out the courses in Algo Academy on the website.

Take me to Algo Academy

I’m going to keep it short, but, as they say….

This is the beginning of everything…

: )

Trade well and prosper!

Simon

Information Ratio = Information Coefficient × √(Breadth)

​ Where:

• Information Ratio (IR): This measures the risk-adjusted return of a portfolio manager’s active strategy, i.e., how much excess return (alpha) they generate relative to the risk they take.

• Information Coefficient (IC): This is a measure of the manager’s skill or the correlation between their forecasts and the actual future returns. A higher IC indicates better forecasting ability.

• Breadth (B): This refers to the number of independent investment decisions or opportunities a manager makes. In essence, it’s about how diversified the strategies are.

In short, for any amount of ‘skill’, alpha increases with diversification (of strategies, of bets, of markets)!

I know we all want “quick, actionable take-aways”, but the reality is that foundational principles of a strategy development process is at the core of successful trading, and you more than likely do not have half of this in place like you should. So, while this is ‘foundational’, and can only be covered briefly, don’t skimp on reviewing this stuff. It’s only in the Algo Collective that we’ll be able to take the time to deep-dive how to set this all up in a highly practical way. Believe me, once you have a pipeline for strategy development, you’re done! You churn out strategies that are more robust, quickly drop bad ideas and refine your portfolio quickly. You can focus on risk management, other research and constant review, while your trading takes place automatically in the background. At least, that’s my approach.

Part II with Dr Tom Stark here:

As I think about building a robust and efficient strategy development pipeline, probably the most critical and overlooked principles relate to the need to do research prior to back-testing. Too many traders rush into testing strategies without first validating their hypotheses or setting themselves on a sound quantitative platform.

A sound research process is where everything begins, and it’s what separates a disciplined quant trader from someone simply chasing the next flashy back-test. You need to build a hypothesis, test it, and then methodically attempt to invalidate it. Look at the process like a data scientist—not someone who just wants to brag about their best back-test result. Pause here. Have you honestly tried to invalidate before? Be honest with me! See how ego gets in the way? These things count my friend. They do.

The shortfalls of the ‘back-test to build’ methodology are substantial. Path dependency, missing trades, and hidden risks are just a few of the issues that arise when we treat back-testing as the starting point. I guess the main issue I have always seen with this approach is that it sort of assumes you ‘already have a strategy to test’ before you begin right?

How did you get said strategy?

The alternative: to test little ideas, piece by piece, allows you to ‘build from the ground up’. You’ll understand and trust your end-product so much more. A key issue with back-tests, as we mentioned in the show, are that they rely on a singular historical path, ignoring the trades we filtered out. Will these same sorts of trades be filtered in future? What if they aren’t? A disciplined process ensures that we test ideas from all angles, probing for weaknesses rather than simply running tests that confirm our assumptions. This approach helps mitigate the over-fitting that often plagues strategy development, giving you confidence in your system’s ability to perform in out-of-sample conditions.

Yep, unfortunately mindset and emotion still play a critical part in quant trading!

The key to success in systematic trading is having a repeatable, methodical process that allows you to build strategies that are both robust and adaptable. By focusing on research first, followed by rigorous testing and validation, you create a “production factory” for strategies. This factory doesn’t shy away from failed ideas but moves efficiently through them until you uncover strategies that work consistently.

So, does it help to bullet point a few ideas? Sure, but obviously not as much as taking this stuff, sitting with it, and making it your own, based on the skills and tools you currently have. The reality is that the process is different depending on the markets, time-frames and strategy-types you trade. Some guidance:

• Our goal is to be grounded on a sound quantitative platform — we want to avoid fooling ourselves, but we also want to broaden our search capabilities to find fleeting edges. Begin with proper handling of data, using good software, understanding the markets. Understand how back-testing engines work.

• Adopt an institutional mindset — I get this is hard to grasp initially but start by at least considering that there is a more institutional mindset. Focus on uncovering clues in data, not perfection; focus on risk; focus on your specific objectives; pay no heed to what others are doing; be ‘portfolio first’ minded; and essentially – build a development platform.

• Set realistic expectations — build for where you are at and what you need. Spend some time building a set of strategies that play well together before even deploying a lot of capital live (deploy some for training). Run imperfect strategies (there’s no holy grail) and over time you’ll make them vastly more productive at a portfolio level.

• Define objectives — clearly identify risk, diversification, markets, time-frames, and when you want the strategy to work along with when it’s expected to fail. What research premises is it based on? Document it.

• Start with research before back-testing — do not jump directly into testing a ‘strategy’. Test behaviours in the market, unlinked to strategy concepts. See if narratives can be backed up statistically. Think about how you’d generate a strategy out of that knowledge. We live in a world where ‘truth is relative’, trading will show you that just aint so. ; )

• Use hypothesis testing — create a hypothesis and conduct ‘proof of concept’ testing to validate the idea before moving on.

• Test ideas from all angles — look for weaknesses and eliminate ideas that lack statistical significance. Look at all the trades, stress test ideas with ‘what if’ analysis that isn’t even in the back-test.

• Avoid path dependency risks — ensure that the strategy works regardless of where the historical data starts or which trades are excluded from a back-test.

• Understand and focus on risk management — “where could this go wrong?”. Don’t ignore that one test you did that showed everything behaving badly! This will drive you immediately toward ‘multi-model’ or ‘ensemble’ deployment where you try to be less ‘exactly right’ and more ‘right on average’. This is ‘institutional thinking’ at work.

• Build a portfolio, not just a single strategy — you know this already. You aren’t building strategies in isolation, remember their role in the portfolio. If you’re just starting out, ignore this, build that one first thing.

• Use robustness testing methods diligently — yes of course you need to deploy techniques such as Out of Sample, Walk Forward Analysis, Monte Carlo simulations, Variance Testing, and Stress Testing. These can be tools in the research phase not just ex post facto tests.

• Keep strategies simple — complexity often leads to over-fitting. Aim for simplicity with well-executed strategies.

• Keep costs down and be efficient — allocate capital efficiently, net out trades, reduce commissions. All this stuff becomes extremely important.

• Build tools for the job — Dump data to Excel, or use Python or R or whatever it is for you, and streamline the analysis.

• Understand the metrics that apply — know the performance metrics (e.g., Sharpe ratio, maximum draw-down (it’s just one number!) and how they relate to your strategy’s effectiveness. Different metrics for different objectives. Understand your tool kit.

• Review and refine continually — iteratively improve the process based on research feedback and real-world performance data.

What is Research?

Research provides the blueprint for development. What inefficiency are you trying to exploit? Is there a plausible economic rationale for that? For instance, trend followers assume that price momentum persists due to under‑reaction; mean‑reversion strategies exploit temporary dislocations; statistical arbitrage looks for relative mispricings among correlated assets.

Conduct exploratory statistics: before back-testing, test whether the signal has predictive power. Use regressions, auto-correlation analyses or non‑parametric tests to see if returns respond to the signal across different assets and regimes. Evaluate parameter stability by plotting performance surfaces.

Research also embeds robustness testing into each component we test, so that, by the time we are robustness testing the strategy, we’ve already gained a lot of confidence in it. Say you have a hypothesis that extreme moves quickly revert: test every instance of it; over every possible ticker; in different regimes. Where do the results cluster? Over what kinds of stocks or futures? How correlated are they if they occur together? What time-frames are we operating in? What levels are important? Does the thing that works in period one also work in period two? What buckets can the results be divided into? Before you know it, you’re developing conclusions that result in meaningful strategy components & filters.

Research is the process of validating hypotheses, so it’s an effort in being scientific in our thinking. We want to identify assumptions, be open about them, don’t hide them subconsciously. The more we try to document the process we follow in our research, the more we can systematize and automate it. The faster we can work to validate ideas, the more we get done, and this is half the battle in such a competitive marketplace.

Here’s the key: if you have built the strategy on research, you can test it in context. Your view of it’s robustness out of sample is based on how many tests your ideas have already passed to get to this point. Basically, back-testing is just one of the tools in your tool-kit, it’s not the solution.

Conclusion: Research First, Back-Test Later

So why must research come before back-testing? Simple. Without a clear research foundation, your back-testing efforts are blind. Research:

• Builds hypotheses that make sense in the market context.

• Defines the risk-reward profile you’re chasing, so back-testing doesn’t mislead you.

• Validates assumptions and prevents over-fitting.

• Gives you confidence that your strategy is grounded in real-world data, not just market noise.

Put simply, back-testing a ‘finished model’ is a confirmation tool, not a discovery tool. Don’t rush into it. Prioritize your research, and only then will you have the clarity and insight to back-test with confidence.

Everything else I’ve got to say on the topic (and there’s a lot) will be built out in the Algo Collective community. Launching January 2026. I plan to deep-dive robustness testing methods inside the context of a systematic development path. See you on the inside.

Stay logical, listen to the outliers.

Simon

Get in Touch with Tom:

Dr Thomas Starke on Substack

A wonderful chat with Dr Tom Starke who is on Substack here! We’ll be doing workshops with Tom in the Algo Collective membership, check it out! Stay subscribed as these workshops are dropping soon and are extreme value for money in the Collective for the first 50 members!

In today’s competitive trading world, many retail traders fall into the trap of hunting for that elusive “perfect strategy”—the one signal or indicator that will turn everything around. But as Tom Starke, an institutional quant trader, highlights, this approach is fundamentally flawed. To build truly robust and successful strategies, traders must adopt a mindset and approach grounded in process, risk management, and scientific thinking. Let’s dive into what it means to build systematic strategies from an institutional perspective and how retail traders can level up their game.

1. Why Most Traders Fail: The Missing Third Dimension

1.1 Start with the End in Mind: Define Your Objectives

Too often, traders start by looking for signals or strategies that seem promising. However, without a clear objective or understanding of the underlying risk, success remains elusive. This is a trap many retail traders fall into, starting with high hopes but lacking a plan. A critical step in building a robust trading strategy is to define your objectives upfront.

For instance, are you trading your life savings, or is this speculative capital? If it’s your retirement fund, your strategies need to be far more risk-averse, with a long-term horizon. On the other hand, speculative trading may allow for more risk but still requires a disciplined approach.

1.2 Trade Like a Business, Don’t Gamble

Think of your trading portfolio as a business. It’s not just about finding a shiny new signal. You need to account for everything that goes into running a successful operation: data acquisition, costs, market knowledge, tools, counterparties, and more. Similarly, institutions like hedge funds or pension funds don’t just focus on one strategy. They focus on the entire business—how they allocate capital, manage risk, and sustain their edges over time.

1.3 Move Beyond Narrative: Embrace Scientific Thinking

The retail trader is often drawn to narratives—the stories behind the trades or the next big indicator. But Tom Starke emphasizes that institutional success comes from evidence-based research and rigorous hypothesis testing. The best quants don’t chase stories; they rely on data to uncover the truth. This requires learning how to interpret data scientifically and using statistical techniques to validate signals.

A common mistake made by retail traders is the pursuit of a “magic signal,”. But these signals, or a single metric (like ‘win rate’) are often devoid of context and fail to account for the complexities of the market. As Starke notes, scientific thinking leads to an understanding of how signals function within broader systems—what risk they carry and whether they remain robust across different market conditions.

• Start with the end in mind. Things will take time, don’t expect perfection at the outset.

• Stay simple & robust at the outset. Keep expectations low. Buy yourself time to learn the ropes and succeed. Don’t burn out.

• Trade real money as soon as possible.

• Keep your day job, it keeps the pressure off.

• Run it like a business. Have a business plan.

2. Define the Game Before You Play It: Objectives & Constraints

2.1 Understand Capital Size & Feasibility

Your trading capital significantly influences your strategy’s viability. For instance, small retail accounts often face issues like slippage and higher execution costs compared to large institutions, which have access to better liquidity, lower spreads & advanced order execution algos. Tom Starke stresses the importance of understanding the limitations of your capital. A strategy that works with $100 million may not work for a $10,000 account. Furthermore, cost drag and turnover are hidden killers that retail traders frequently overlook. Conversely, many strategies that trade fine on a few hundred thousand dollars, are hard to scale even to $5 million. An important consideration if your objective is to trade for a fund.

2.2 Clarify Your Risk Profile

The next question you must answer: How much risk are you willing to take? Starke advocates for clear risk profiling, not just focusing on potential returns. Institutions prioritize stability and lower risk over time, aiming for consistency, not “home runs.” Retail traders, however, often chase high-risk, high-reward strategies that lead to catastrophic losses when things go wrong. By defining your risk tolerance early, you can ensure that your strategies align with your long-term goals.

• Capital is not homogenous: high risk returns <> low risk returns

• In institutions, mandates (objectives) anchor everything

• Account size determines viable strategies

3. The Institutional Trifecta: Risk, Robustness & Execution

3.1 Risk Management as the Foundation

Risk management is the bedrock of institutional trading. The strategy signals themselves are less important than how those signals are weighted in a portfolio. A profitable strategy can still lose money if it is sized incorrectly. This is why Starke mentions the Kelly criterion—a formula that helps determine optimal position sizing based on your edge (there are other options and additional considerations, but it’s a start). Without the right sizing, even the best strategy could fail due to improper risk allocation.

3.2 Robustness Over Optimization

Robustness means that a strategy will continue to work in different market environments, not just under the conditions it was tested. Too often, retail traders optimize their strategies to fit historical data, forgetting that past performance is not always indicative of out of sample results. Starke argues that (most) institutions prefer lower-risk, stable returns over “home runs.” Robustness testing—using walk-forward analysis, Monte Carlo simulations, and out-of-sample testing—helps ensure that your strategy won’t just perform well on paper, but the edge will continue to play out in live markets.

For an institution, ‘edge’ isn’t just ‘expectancy’.

“Expectancy”=Probability of (”win” )×”Avg Win” - Probability of (”loss” )×”Avg Loss”.

Expectancy is a vital metric and a good theoretical proxy for edge – it captures the idea of having odds in your favour. But a truly valid edge in trading is more than just a number; it encompasses risk-adjusted performance, consistency, and the ability to actually realize that expectancy in live markets. A comprehensive definition of edge might be: a repeatable strategy or advantage that produces positive expected returns after accounting for risk and costs, and that can be executed with discipline to yield persistent outperformance. Achieving that is the holy grail that every trader, from the ivory-tower quant to the instinctive macro guru, is ultimately seeking.

3.3 Execution: A Hidden Pillar

Many retail traders overlook the importance of execution. Slippage, spread, and market impact can all eat into profits. Starke highlights that even small improvements in execution can make a significant difference over time. Institutions spend significant time refining their execution processes, reducing transaction costs, and minimizing slippage. Retail traders can level up by improving their execution methods, ensuring that they pay attention to every aspect of their trading costs. A good order management system or a basic knowledge of IB order execution algos might help enormously.

• Strategy signals matter far less than portfolio construction

• Tiny errors in position sizing can destroy edges

• Retail pay higher costs & must work with less capital. They must compensate through smarter strategy design and efficient use of capital

• Retail traders have access to strategies that institutions are too large to bother with

4. The Real Work: Building a Process for R&D

4.1 Research First, Back-test Later

Starke stresses that back-testing should come at the end of the research process—not the beginning. Far too many retail traders fall into the trap of optimizing strategies for past data before they even know what they’re trying to accomplish. Institutional traders, however, build hypotheses first. They define their objectives and constraints, test hypotheses, and then validate them using back-testing last. Back-testing is only useful when you’ve already answered key questions about risk, strategy design, and market conditions. Why? Because it’s just not good research. It’s prone to overfitting; ignoring blind spots; missing context. Research will give you an intimate understanding of the edge you are trying to capture, and that will drive your strategy design.

4.2 Evaluate Signal Significance

Once you have a hypothesis, you need to determine whether your signals are statistically significant. The goal is to determine whether a signal is predictive, not just a product of market noise or the select group of filters you attached to it. Retail traders often base their strategies on signals that appear strong in nicely ‘filtered’ back-tests but fail in real-world conditions. Tom recommends using statistical tests to assess the strength of signals before committing to them. Are your signals actually predictive, or are you just lucky with the sample that was in your back-test?

4.3 Build Robustness into Your Process

The heart of an institutional research process is its focus on robustness. Institutional quants build multiple layers of testing into their process, such as walk-forward analysis, stress testing, multi-market testing, Monte Carlo simulations and more. These are baked right into the research process, not applied after the fact.

These methods simulate various market conditions to ensure that the strategy performs well when it is supposed to. Retail traders can do the same, running their strategies through different market regimes to see where performance is generated, and when risks emerge out of the dark.

4.4 Path Dependency: An Example of a Back-Testing Flaw

One of the most common mistakes retail traders make is seeing the single path of a back-test as a definitive guide to the future. But back-tests can often be “path-dependent”—a strategy may look profitable because of the specific time frame or sequence of events chosen. A single back-test is just a single path among many, many possible paths. Instead, we must look for strategies that are not dependent on specific starting points, or a highly specific sub-set of the total universe of possible trades. Don’t be afraid to look at worst case scenarios, worst possible trades, etc. Try to invalidate your hypothesis. Focusing on the weak spots is the only unbiassed way to know whether it can be reinforced to handle the likely strain or not.

• Develop a systematic pipeline for the development of systematic strategies

• Automate it where you can to compound your search area

• Spend more time researching a concept, prior to pinning exact filters, entries and exits to it and calling it a strategy

• It’s trading, not true science, so stay creative

• Reduce degrees of freedom early, invalidate quickly, move on to greener pastures

• Remember that statistics are averages, usually ignorant of sequence risk or events we haven’t seen before

• Build around the concept of avoiding catastrophic failures

• Assess all possible trades, not just the filtered ones

• Consider sequence of trades, and correlations

• Map to regimes, and expectations

• Use as many robustness testing methods as possible, but not the ones irrelevant to your particular model

• Step away from the screen and sit under an apple tree for a while meditating on what you’re trying to achieve

• Know your metrics, and which are relevant to the task at hand

• You will think more in terms of ‘risk drivers and return profile’ than in ‘mean reversion’ or ‘trend following’

5. Combining Strategies into a Unified Portfolio

5.1 The Strategy of Strategies

A robust trading system is more than just a collection of individual strategies. It’s about portfolio construction—how different strategies work together to reduce risk and increase consistency. Think of each strategy as a “product” with its own risk profile and return characteristics. When combining strategies, you should consider their correlations, how they behave in different market environments, and how they complement each other.

5.2 Diversification in Action

Starke stresses that diversification is not about adding more assets to your portfolio but about finding uncorrelated drivers of risk and return. For instance, you might combine mean-reversion strategies with trend-following strategies, as they tend to perform well under different market conditions. A sufficient number of discrete strategies aggregated can behave like one continuous, dynamic portfolio. Positions can be netted, multiple variants can throttle exposures, bet sizes shrink (as can commissions) and risk can be more easily managed.

Additionally, your ‘average returns’ are more likely to play out in the future since you aren’t trying to pick the ‘one thing’ that is going to succeed next year. Hint, it’s never what succeeded last year!

5.3 Sizing and Turnover

Position sizing is crucial to portfolio construction. Even a good strategy can fail if the position size is too large or too small. Stop and think about what it means to use capital efficiently. This is especially important for retail traders who often have less capital and higher transaction costs. Efficient portfolio construction ensures that each strategy works harmoniously within the larger framework. For examples, check out the podcast with Corey Hoffstein (Ep 27) where he talks about ‘return stacking’ – a stock portfolio can often add futures (or other leveraged products) without requiring additional capital.

• Diversification doesn’t mean more tickers, it means uncorrelated drivers

• Seek to quantify diversification

• At every possible opportunity, reduce your reliance on any single edge

• Design strategies with the portfolio in mind

6. Mindset Shift: From Retail to Institutional Thinking

6.1 Focus on the Process, Not the Signal

The first mindset shift is moving away from focusing solely on trading signals and indicators. Institutions think about the process—how strategies are built, how they fit together in a robust portfolio, how to size positions, and how to manage risk. Starke emphasizes that without a defined research process, you risk making decisions based on biases, narratives or overfitting.

6.2 Get Comfortable with Iteration

In institutional settings, research is an ongoing process. Institutions don’t expect strategies to work perfectly on the first try. Starke’s experience in academia and industry has taught him to be comfortable with iteration—testing hypotheses, refining models, and validating results. As a retail trader, adopting this iterative mindset (and automating where possible) allows you to build strategies with more rigor and avoid emotional decision-making – dropping bad ideas quickly.

6.3 Don’t Fall for Quick Fixes

Another critical mindset shift is to avoid falling for quick-fix solutions. Retail traders are often sold “simple” strategies or tools that promise instant success, but these rarely deliver in real-world markets. Institutional traders take a long-term view and focus on building sustainable, evidence-based strategies. They work in teams, they spend time on automation, and they stay accountable – excessive risk taking isn’t an option.

• It takes time to know what you don’t know

• Build your network: cross-pollinate ideas; stay accountable

• Take the mindset of a professional sceptic

7. Conclusion: Key Takeaways for Traders Ready to Level Up

Building a robust trading strategy is not a one-step process. It requires discipline, scientific thinking, and a commitment to continuous improvement. Here’s what you need to do:

• Define your objectives clearly: Understand your risk tolerance and the capital you’re willing to invest. This will shape your strategy and trading approach.

• Focus on risk management: A good strategy is only as good as the way you manage risk. Proper position sizing and portfolio construction are essential.

• Build a process: Follow a structured, evidence-based approach to research and strategy development. Don’t jump into back-testing without a clear hypothesis and an understanding of your risk.

• Diversify across strategies: Combine different strategies that complement each other to reduce risk and smooth returns.

• Shift your mindset: Focus on building a process, not chasing a signal. Be prepared to iterate and refine your strategies based on real-world data.

If you adopt these principles, you’ll be well on your way to building institutional-grade strategies that can stand the test of time.

Never give up!

Get in touch with Tom

Substack

Linked In

X

Website

1. Overview

Rob Hanna is a short-term systematic trader and researcher, founder of Quantifiable Edges and portfolio manager at Capital Advisors 360. He trades roughly 15 models across:

• S&P-500/Nasdaq100 large-cap stocks

• A diversified ETF universe

• VIX options and VIX-linked ETFs

• Tactical bond–equity rotation strategies

He describes himself as “90% systematic”, using research-driven indicators for entries/exits, with discretion mainly in position sizing and risk-off decisions around scheduled events (Fed, elections, etc.).

Core philosophy:

• No trade without a quantified edge – he only trades setups whose historical behaviour he has studied in detail.

• Research first, system second – he studies market behaviour (e.g., “what happens after a 5-day low in an uptrend?”) and only then wraps rules around robust edges, rather than optimizing indicators ex-post.

• Multiple lenses on the market – breadth, seasonality, term-structure, Fed behaviour, volatility, etc., are combined into composite views.

• Anxiety reduction via data – the research is explicitly there to “take the edge off anxiety” and help him stick with positions where the measured edge still exists.

2. Key Concepts and Definitions

2.1 Research-first edge and model construction

Definition / practice

• Start from questions about market behaviour (e.g., after big sell-offs, before Fed days, under specific breadth conditions).

• Run large numbers of historical studies (tools: TradeStation, AmiBroker, RealTest, Excel, Norgate data) to quantify outputs. Use metrics that fit the task and know your metrics in-depth. For example, the Sharpe ratio might be irrelevant to your trend following strategy. Profit factor is a key for many of Rob’s models.

• Build models that exploit simple, robust conditional tendencies; avoid heavy parameter optimization and “curve-fit rescue missions”.

He explicitly criticizes the “classic rookie” approach: decide to build an RSI-2 system, optimize entry/exit thresholds, then bolt on filters to remove historical losers. Instead he prefers:

“Learn how the market has performed under situations that are repeatable… Then creating a model to take advantage of whatever edge you find becomes a lot easier.”

This is effectively research-driven feature discovery, followed by simple rule design.

Risk implications

• Because the edge is defined first, robustness is baked in rather than retrofitted.

• Still uses standard controls: out-of-sample tests, alternative parameter choices (“parameter ranges that all work”), and economic narrative (e.g., why institutional ownership supports mean reversion in large caps).

If there’s one area that the vast majority of traders could improve on, it’s this: research. Research takes time, so developing a process for research is the key. Once this process is in place, systematic trading can start to look and feel easy, but the newbie doesn’t see how long it took for the expert to develop that process. As an exercise, ask ChatGPT to analyse PHD-level research techniques and start applying these to your trading. Thank me later!

2.2 The Aggregator – multi-lens market bias filter

The Concept

The Quantifiable Edges Aggregator is a composite indicator that rolls up Rob’s active studies into a single short-term market bias measure. Each study expresses an expectation for SPX over the next few days; the Aggregator blends these into a net expectation series (plotted as a green line) where:

• 0 ⇒ bullish short-term expectation

• < 0 ⇒ bearish short-term expectation

In practice, he shows the Aggregator every night in his newsletter and uses it to gate his stock and ETF strategies.

Trading logic

• When Aggregator is bullish and the market isn’t already overbought
  – he is willing to deploy long mean-reversion and other long-bias models; short setups are often disabled.

• When Aggregator is bearish
  – long mean-reversion models stop taking new trades; short models activate.

• When Aggregator is neutral
  – he typically stands aside from new equity entries, letting existing positions run down.

He explicitly frames this as “a rising tide lifts all boats”: if the broad market conditions are supportive, individual stock edges are more reliable; if not, you need to be a “really good stock picker”.

Educational angle

The Aggregator is a powerful example of:

• Combining many weak but statistically significant edges into a single meta-signal.

• Using market-regime conditioning to decide which strategy cluster (long, short, flat) should currently be active, rather than forcing all models to be agnostic to regime.

2.3 Breadth indicators and custom filters

Hanna leans heavily on breadth & filter logic, both via standard indicators and custom constructions.

2.3.1 Standard breadth thrusts

His upcoming breadth course uses and extends classic breadth tools:

• Zweig Breadth Thrust, McClellan Oscillator, advance-decline lines, tick / TRIN, etc.

• His Trip 70 breadth thrust looks at surges where a high proportion of stocks close above their 10-day moving average (70%+), a variant of classical thrust definitions.

These thrusts act as context filters: e.g., after powerful breadth thrusts out of oversold conditions, short setups in equities are de-emphasised.

2.3.2 Capitulative Breadth Indicator (CBI)

The Quantifiable Edges Capitulative Breadth Indicator (CBI) is Hanna’s flagship breadth tool:

• Constructed from signals generated by his Catapult system, which buys individual S&P-100 stocks that have undergone “extreme (often capitulative) selling.”(Quantifiable Edges)

• The CBI is simply the count of Catapult triggers currently active across the large-cap universe; readings thus measure how many big-cap stocks are in capitulation at once.(quantifiableedges.com)

Key levels (rules of thumb):

• CBI ≥ 7 – “elevated” breadth capitulation.

• CBI ≥ 10 – historically strong intermediate-term bullish edge for SPX, especially when the long-term trend is still up.(quantifiableedges.com)

Educationally, CBI is a clean example of building breadth from system triggers rather than raw up/down counts: you can define breadth over your signal logic, not just advances/declines.

2.3.3 Custom sector and universe filters

• Stocks: S&P-100 + remaining S&P-500 names (split into “Swing 100” and “Swing 400” models), with no overlap – a stock can belong to one model only. This keeps position sizing in check, the key risk management technique for mean reversion models.

• Sector caps: e.g., Swing 400 limits exposure to any one sector to 30% of portfolio, to avoid “all-in financials” or similar sector pile-ups. This kind of thing is easily implemented in Real Test with Norgate data.

• ETF universes: baskets of ~46 liquid ETFs spanning cap-segments, sectors, and countries, deliberately avoiding near-duplicates (SPY vs IVV vs VOO).

2.4 Mean-reversion, momentum & seasonality models

2.4.1 Large-cap stock mean reversion

Universe:

• S&P-500 / 100, Nasdaq-100 stocks only – he avoids small caps because the lack of institutional sponsorship makes them more prone to “falling knife” behaviour and structural problems (bankruptcy, dilutions, etc.).

Core ideas:

• Simple price-based mean reversion: multi-day lows, short-term RSI, distance from moving average, etc.

• Negative skew is acknowledged: “up up up big drop” is the standard equity mean-reversion pattern.

Risk management:

• Position sizing – limits per-name and per-sector exposure; total daily new exposure is throttled so he doesn’t “load the boat” on one ugly day (accomplished through the deployment of multiple models to ‘spread the trading out’).

• Scaling-in models – e.g., Catapult scales in as selling intensifies, smoothing entry prices and avoiding oversized bets at first touch.

• Aggregator gating – he only deploys long MR when short-term market studies are bullish, and vice versa for shorts.

He also runs short stock MR (“Icarus”) that fades high-flyers extremely stretched to the upside, which tends to perform when long MR is struggling. Together with Catapult, this creates a pair of complementary MR engines.

2.4.2 ETF mean reversion

Logic is very similar:

• A diversified ETF list (indices, sectors, countries). Care needs to be taken in constructing an ETF universe – pay attention to duplicates, costs, liquidity).

• Model may hold up to four ETFs at once, typically 25% each, long or short based on the signal.

• Uses similar overbought/oversold indicators, but parameter ranges don’t differ dramatically from stock MR – the main difference is volatility scale.

The ETF MR model is opportunistic, not always in: it is flat when conditions are neither stretched nor attractive.

2.4.3 Momentum and seasonality / tactical allocation

Hanna’s Momentum & Seasonality model:

• Rotates among a small set: S&P (SPY), Nasdaq (QQQ), and bond ETFs, effectively a narrow tactical asset allocation system.

• Drivers include:

  • Price momentum / trend filters

  • Seasonality (calendar patterns, holiday effects, etc.)

  • Simple cyclical indicators (from his Market Dynamics course)(quantifiableedges.com)

The model is deliberately simple – a small number of ETFs and signals – prioritising interpretability and robustness over fancy optimization.

2.5 VIX term structure & “volatility ladders”

Of particular interest to me were Rob’s VIX trading strategies due to their usefulness as a hedge in times of crises, and because they employ more than just price data (they look to the VIX futures curve - whether in backwardation or contango as a critical filter to his models). Trading volatility (through the futures, options or ETFs) can be extremely risky but given the strong edges that are present in trading a consistent down-trending market, it’s always of interest to me how traders find a way to profit while minimizing the risks inherent in these models.

2.5.1 Contango and Backwardation – the basics

Think of the VIX futures curve as prices for volatility at different expiries:

Typical (contango):

Dec 17 ──► Jan 19 ──► Feb 21 (upward-sloping curve)

• Future months trade higher than near months.

• VIX ETPs (e.g., VXX, UVIX) that roll daily from front month into second month bleed value because they are constantly selling cheaper and buying more expensive futures.

Crisis (backwardation):

Dec 30 ◄── Jan 27 ◄── Feb 24 (downward-sloping curve)

• Near-term fear is extreme; the curve inverts.

• Now the VIX ETP roll yields positive carry: as days pass, you roll from high-priced near futures into lower-priced longer ones.

Hanna uses this term-structure behaviour as a primary risk switch for short-volatility trades, and as a source of opportunity for relative-value trades.

2.5.2 Short-volatility and crisis risk

He runs several short-volatility models in VIX ETFs/futures, recognizing a strong long-run edge (vol is usually overpriced; term structure usually in contango). But:

• VIX ETPs can absolutely explode in stress (5–10x moves), so position sizing and stepping aside in stressed regimes are non-negotiable.

• He stresses two main controls:

  • Exit or cut risk when the curve flips from contango into backwardation.

  • Stand down when VIX levels or realized vs implied spreads pass certain thresholds (e.g., VIX > ~25–30, implied >> realized).

He also uses S&P overbought/oversold as an additional lens: his award-winning paper “Chicken & Egg: Should you use the VIX to time the SPX? Or use the SPX to time the VIX?” shows that using SPX action to time VIX trades can be more effective than the reverse, and forms the basis for sample VIX-timing strategies.(quantifiableedges.com)

Simple rule of thumb from that work:

• When SPX is strongly oversold, probability of a rebound is high → favourable time to short VIX.

• When SPX is strongly overbought, short-VIX edge diminishes; adding long-vol exposure as protection can make sense(quantifiableedges.com).

2.5.3 Volatility ladders – options-based crisis alpha

His Volatility Ladders strategy trades UVIX options using:

• Calendar and diagonal spreads (e.g., Jun vs Jul 140 calls)

• Vertical call/put spreads when appropriate

• Relative-value between different VIX maturities, especially around big events (tariff scares, election risk, carry unwinds).

He spent substantial effort building a historical database of VIX options and synthetic spreads to backtest these ideas, incorporating realistic assumptions about bid–ask slippage and achievable prices.

Key idea:

• Use mispricings in deep-out-of-the-money options and curve dislocations to get paid to hold tail exposure:

  • Sell rich parts of the curve, buy cheap optionality further out.

  • As those relative mispricings mean-revert, profits from spreads can be recycled into maintaining a residual long-gamma/long-vega position.

This creates the possibility of crisis alpha: when his equity models are under pressure during volatility spikes, the long-vol legs in Volatility Ladders can pay off heavily.

2.6 Fed-day and macro-event filters

Hanna is well-known for his Fed-day research:

• Long-term studies show that Fed days have historically produced returns several times larger than average SPX days.(Quantifiable Edges)

• The edge is conditional: it is stronger when there has been fear going into the day (e.g., SPX down into short-term lows) and weak or absent when the market has rallied into the meeting.(quantifiableedges.com)

Crucially, he finds much of the edge occurs before the 2pm announcement (from prior close to early afternoon), not after – consistent with “insiders and positioning” doing the work.

These studies are examples of:

• Event-driven filters that can be used to suspend certain models (e.g., short-vol, aggressive shorts) around Fed days.

• Short-term tactical trades (overnight or intra-day) for those who want to exploit the quantified edge; much of this is compiled in his Guide to Fed Days.(quantifiableedges.com)

3. Debates, Controversies, and Best-Practice Themes

3.1 Mean-reversion vs trend following

• Hanna is candidly biased toward mean reversion, especially in equities, because he can see clear, repeatable edges in extreme moves and capitulation. It also suits his contrarian personality and the return profile he’s looking for in his trading.

For education, this is a good case study in strategy–personality fit and in the dangers of forcing yourself into a style (e.g., chasing big multi-month winners like NVDA/TSLA) that your research doesn’t support.

3.2 Discretion vs pure automation

He is ~90% systematic, but reserves discretion mainly for:

• Sizing and stepping aside (e.g., ahead of known binary events like elections; when volatility term-structure is doing something not often seen historically).

• Some VIX trades where practical considerations (liquidity, strikes available) require judgment.

I guess the question is how much discretion is acceptable before you contaminate your edge? Hanna’s compromise is that entries/exits are always indicator-defined; discretion changes how hard he leans into them, not whether the signal exists.

3.3 Short-volatility ethics: edge vs blow-up risk

Short VIX ETPs are famously dangerous; “volmageddon” episodes have blown up products and retail accounts. Hanna’s approach is cautious:

• He emphasises that the long-term edge is real but only if position sizes are modest and you stop playing when regime changes.

• His more advanced implementations use spreads and ladders, explicitly limiting maximum loss and sometimes holding net long vol.

This sits squarely in the ongoing debate: is systematic short volatility a legitimate income strategy or just “picking up nickels in front of a steamroller”? His framework shows how to do it with explicit tail-risk budgeting rather than denial.

3.4 Overfitting and robustness

By starting from historical conditional behaviour (e.g., Fed days, breadth thrusts, capitulations) and then encoding simple rules, Hanna attempts to stay on the safer side of the overfitting line. But key best-practice themes in his work:

• Use multiple independent edges (breadth, seasonality, vol term-structure) so performance isn’t reliant on any single anomaly.

• Control exposures by model, asset, and sector.

• Use breadth of evidence (many studies, long history) rather than a single impressive backtest equity curve.

His Aggregator is also a response to study collision: when many studies conflict, the Aggregator nets their expectations rather than cherry-picking the nicest ones.(quantifiableedges.com)

4. Practical Applications and Examples

Here are some lose examples of how this would actually look in a model.

4.1 Combining breadth filters with equity mean-reversion

1. Universe: S&P-500 large caps only.

2. Signal: Buy when a stock closes at a 5-day low, above its 200-day MA, with short-term RSI below X.

3. Breadth & Aggregator filter:

   • Only go long when:

     • Aggregator > 0 (market-wide bullish bias), and

     • CBI < 7 (no massive capitulation yet) – this version is “normal dip buying”, not crash-chasing.

4. Risk:

   • Max 30% per sector, fixed fractional position size per signal.

   • Limit to N new names per day; cap portfolio at e.g. 10–20 positions.

You can build a companion Crash MR model that only activates when CBI ≥ 10, with bigger, shorter-horizon bets – effectively a crisis-buying specialist.

4.2 ETF mean-reversion basket

1. Universe: ~40 liquid ETFs (broad indices, sectors, major-country ETFs).

2. Signal: Take long/short positions in ETFs whose Z-score vs 20-day mean exceeds threshold; overlay mild trend filter to avoid shorting in roaring bull markets or buying in entrenched bear trends.

3. Exposure control:

   • Up to four ETFs at a time; 25% capital each; can be all long, all short, or mixed.

   • Use Aggregator to throttle: scale down gross exposure when Aggregator is near zero.

This is close to Hanna’s described ETF swing model.

4.3 Simple SPX-to-VIX timing rule

Based on Chicken & Egg:

• If SPX 3-day RSI < 20 (strongly oversold) and VIX term-structure still in contango, initiate a small short VIX ETF position (or equivalent options spread).

• Exit when RSI crosses back above ~50, or when term-structure flips into backwardation.(quantifiableedges.com)

4.4 Fed-day overnight trade

Using his Fed studies:

• When SPX closes at a multi-day low before a scheduled Fed meeting, buy SPY at close and hold until next day’s early afternoon (pre-announcement).

• Avoid when SPX closes at 10- or 20-day highs into the meeting.(quantifiableedges.com)

This is a neat example of event-driven quant edges and of “edge playing out before the headline”.

5. Notable Quotes / References

• On abandoning hunch trading: after tracking a “hunches” category, he found it consistently underperformed his quantified setups, teaching him to drop discretionary guesses.

• On research and anxiety: researching “what the market typically does after X” allowed him to stick with trades where he knew he still had edge, and exit when he didn’t.

• On Aggregator purpose: blog posts describe it as a way of turning many active studies into “a composite estimate of where the market is likely to go over the next few days,” resolving conflicting signals into a single bias.(quantifiableedges.com)

• On CBI: he calls it an indicator born from his Catapult system, with readings ≥10 historically associated with powerful intermediate-term rallies after capitulation periods.(Quantifiable Edges)

• On SPX vs VIX timing: the Chicken & Egg paper argues that SPX behaviour is often the better driver for VIX trades than VIX for SPX.(quantifiableedges.com)

6. Suggested Further Reading

Prioritising Quantifiable Edges and closely related sources:

1. How the Quantifiable Edges Aggregator uses expectations and risk/reward analysis to establish a reliable market bias – core explanation of the Aggregator, with charts.(quantifiableedges.com)

2. When Studies Collide – discussion of conflicting studies and how the Aggregator resolves them.(quantifiableedges.com)

3. My Capitulative Breadth Indicator and Introducing the Quantifiable Edges Catapult Exit Designer – background and stats on CBI and Catapult system.(quantifiableedges.com)

4. “Finding a quantifiable edge in capitulation selling analysis” – Proactive Advisor article summarising CBI and its use in practice.(Proactive Advisor Magazine)

5. CBI category archive on QuantifiableEdges.com – many real-time case studies of CBI spikes and subsequent market behaviour.(quantifiableedges.com)

6. Fed Study category and A Long-Term View of Fed Days – detailed work on Fed-day tendencies and conditional filters.(quantifiableedges.com)

7. Chicken & Egg: Should you use the VIX to time the SPX? Or use the SPX to time the VIX? – the NAAIM-award-winning paper on SPX-driven VIX timing.(quantifiableedges.com)

8. Quantifiable Edges blog home and archives – ongoing short studies on breadth, seasonality, volatility, and event edges.(quantifiableedges.com)

9. Proactive Advisor pieces on Fed days and breadth – accessible write-ups of his research for advisers.(Proactive Advisor Magazine)

Get in Touch with Rob

Website

X

Linked In

For members of the Algo Collective (https://www.algoadvantage.io/collective) I’ll produce an even more detailed research report (it’s already 14 pages) on Rob’s strategies. See you on the inside!

Stay resilient,

Simon

But first, let me remind you: Algo Advantage is launching COURSES & COMMUNITY. It’s not far off now, check out the new website for a taste and sub to our newsletter (via Substack or the website). The big news is Dr Tom Starke will be leading a live video course for members, and we’re open to feedback on what you’d like to cover. We can evolve with you, and the focus will be “how institutions do research“, this is the art of quant trading, the missing link for most. On top of that there will be weekly AMA’s with me and a whole bunch more. Check it out at www.algoadvantage.io. Get in touch with me to tell me what you’d like to learn!

I think Nick Radge’s edge is actually an architecture: robust, simple, momentum-driven systems stitched together into a portfolio that survives, adapts, and compounds. Across nearly four decades, he’s traded through crashes, chop, and melt-ups; shifted from futures to equities for business reasons; and kept his build-process stubbornly logic-first and comfortingly boring—by design.

Strategy Breakdown

Nick trades nine strategies. All long-only. Australian and US equities and ETFs. Multiple styles, but the dominant driver is quantitative momentum—both absolute (trend-following breakouts) and relative (rank-and-rotate the strongest). That stack gives him serially correlated equity exposures, but with diversified return streams across universes, parameters, and rebalance tempos.

Tactical Asset Allocation (TAA)

Nick runs tactical rather than static all-weather: a small, vanilla roster of ETFs in two buckets—growth (equity indices) and defensive (gold, rates/bonds, select commodities; a small, liquid crypto sleeve in some mandates)—with monthly rebalancing and rules that only hold assets while they’re trending up. If nothing’s trending, revert to cash. Rebalancing keeps single-line exposures from ballooning; the tactile approach cuts drawdowns versus classic “set-and-forget” allocations. Australian and US sleeves are built slightly differently (e.g., one static/binary roster vs. one bucketed “pick-the-strongest” scheme), which adds another sliver of diversification. He’s targeting single digit worst case draw-downs and returns to date have been very impressive. Follow him on twitter where he frequently posts his stats and research.

Key Tenets of the TAA Approach

• Diversify exposures. Split growth/defensive; diversify across AUS/US ETFs; diversify styles.

• Be open to riding whatever trends are present. Positions exist only while momentum is positive; otherwise sit in cash.

• Allocate wisely to defensive, not just offensive assets. Gold and rates matter—especially when equities wobble.

• Let profits run, cut losers short. The edge comes from positive skew, not hit-rate vanity. Catch the big winners.

• Keep it simple and robust. Big, liquid, vanilla ETFs; low parameter count; monthly cadence.

What is TAA?

TAA is an ‘all weather’ dynamic approach that tilts a portfolio toward (or away from) broad asset classes - (such as equities, bonds, commodities, cash) - based on objective momentum in the asset. The broad idea is that you want exposure to ‘defensives’ (assets which should fare better when equities crash), as well as to ‘offensives’ (equities), but never be exposed to anything that isn’t performing (revert to cash). This allows us to ride non-correlated trends in whichever assets are moving. With the rise of liquid ETF’s, the implementation of a TAA portfolio became easier. Select a diverse set of assets, use simple and robust measures of momentum, set desired weights / exposures to different classes, and review on a regular schedule (typically monthly). The goal is to gain equity-like returns with drastically lower volatility.

Nick uses circa 6 large, plain ETFs—some defensive (gold, commodities, interest-rate/bond, some BTC), some offensive (broad equities, global or country specific). Set max weights per line, rebalance monthly, and only hold lines that are rising on simple momentum rules. If nothing qualifies, the portfolio stays in cash. Repeat with certain modifications in different geographies for added diversification.

Dual-Momentum Style Strategies in Equities

Key Principles

• Align with the broader market. Use a regime filter (e.g., index > long MA or breadth up) so you buy stocks when the tide lifts all boats.

• Treat stocks as correlated assets. Diversify at the return-stream level: strategy-type, timeframe, rebalance period, universe, parameters, and market regimes. Let exposures wax and wane over different internal cycles.

• Keep it simple and robust. Prefer few, round-number parameters.

• Follow trend-following math. Hunt outliers, keep the right-tail, cut the left-tail fast. Expect ~45–50% win rates with winners many times larger than losers.

• “Profits are easier over longer periods.” Longer lookbacks tolerate noise, keep you in the outliers & set you up for the larger (easier) returns. More lifestyle, better bang-for-your-buck business model.

Nick runs a couple of relative-momentum models (rank the universe, own the leaders) and a couple of absolute trend models (breakouts/strength filters). Geography matters: the US—heavily institutionalized—leans toward relative momentum; Australia (and similar markets like Canada) is friendlier to absolute trend. Blend both. In crisis, expect correlations to rush toward 1—so TAA is the safety net. Also, match style to strata: some models prefer mega caps, others mine lesser-covered names for outliers.

Australia vs. the United States (Know Your Habitat)

The more institutionalized the market (think: analyst coverage depth, indexing, efficiency), the less friendly it tends to be for absolute trend according to Nick’s research. In the US, Nick runs relative momentum exclusively; in Australia (and similar markets), absolute trend still shines. He also tilts away from the cap-weighted, analyst-swarmed top layer to avoid index-hugging.

Other Strategies

There’s a small allocation to shorter-term mean reversion—useful, but not a headline driver in Nick’s book. The real horsepower is the slow, simple, scalable momentum stack.

Robustness is the Engine; Compounding is the Outcome

If you don’t deeply believe in your strategies, you won’t sit through the equity-curve pullbacks that fuel future growth. Confidence built on logic—rather than hope—prevents Holy-Grail chasing, burnout, and the death of compounding. Treat trading like a business: set objectives, align expectations with reality, and build for your account size and lifestyle.

Portfolio-Level Thinking & Qualitative Factors

There’s always an art to the science. Design for where you’re going (e.g., managing external capital with larger balances, higher diversification, more automation). Qualitative calls still matter around the quant core: stage of life (wealth creation vs preservation), risk tolerance, time available, and interests (perhaps crypto floats your boat). Think of sequencing risk and the impact it could have on your trading if you are nearing retirement. Basically, in a short sequence of events (any shorter-term time frame), the “averages” are unlikely to play out. You could see a severe down tilt right when you want to retire. Suddenly, “the long term” isn’t as important as wealth preservation. This is exactly where great traders generally end up if they’ve had a successful career right? Sequence-of-returns risk is real; lower-vol sleeves (like the “all-weather” TAA) live inside Nick’s retirement account to keep drawdowns single-digit and income withdrawal smoother.

Trading Is a Business (Plan It Like One)

Thinking about these qualitative factors, and other aspects of Nick’s wisdom, reminds me how important it is to actually have a business plan for trading. Actually write one out if you haven’t already. How many strategies will you start with? At what expected vol? How many strategies would you like to be running in 3–5 years? Targeted return? With how much capital? Preferences for data, software, order management? Not to mention the budget/roadmap to get there. That vision keeps you from tapping out right before the outlier shows.

Here’s the personal lens that shaped my build: my north star was to trade external money. That conscious choice—because it’s the most scalable way to compound my efforts—influenced everything downstream. I designed portfolios and software for larger balances, which let me run leaner and broader: more efficient execution, deeper diversification, greater portfolio horsepower. It also fit my temperament: do the job properly, to the best of my ability, and engineer out as many avoidable mistakes as possible. Invest in software to automate and execute a broad range of strategies. Get mentorship from experience experts. Know it would take a few years.

This flows into a favourite theme: the qualitative side of quantitative trading. Your plan isn’t just code and back tests; it’s policy around real-life variables. Decide your preferred strategies, and define when they should be retired. Consider your macro outlook without overfitting to it. Factor in your age and distance to retirement (risk tolerance isn’t static). Be honest about labour: how much work you want to do, how many hours you’ll actually spend at screens, and what you enjoy. These non-numeric constraints shape durable systems that fit you. It’s important.

Get the plan done. Have a vision for how you’ll grow into it. Accept that it requires investment—of time, money, and discipline. Then deploy with confidence.

So How to Spend More Time Fishing?

Keep things robust. Nick doesn’t want to frantically swap models; he wants durable engines that run for years with minimal tinkering. He’s outlasted multiple crises, outperformed plenty of flashier names, and done it without wearing a tie (hard to reconcile with fishing and golf). That’s success by several metrics in my book.

How to make things robust

• Know why your strategy makes money. If you can’t articulate the edge, you won’t trust it when it bleeds. Trend/momentum’s edge is simple: small losses, large wins; no prediction required.

• Use minimal, round-number parameters. Complexity creates scaffolding and stress points. Favor 100/200-day style lengths; keep pairs coherent (e.g., regime and stock filters of similar order).

• Favor longer-term. Markets are noisy. Longer windows are more efficient, harvesting bigger outliers.

• Back ideas with research, logic, and common sense. Over fitting is difficult if the model is built on principle rather than data mining. Build individual models with the portfolio in mind.

• Secret sauce: Optimize only to find the most volatile parameter, then monitor that one most closely and review annually with minimal changes.

Stress-testing the living daylights out of it

• Say no to single-market systems. Prove ideas across multiple markets/universes.

• Skip trades in testing. Drop best and worst fills; see if the equity curve survives without the lucky shots.

• Model frictions realistically. Slippage happens; opens/closings are noisy. Randomize closing or opening prices by a few percent and re-test for variance resilience.

• Use regime filters. A simple index > 200-day (or breadth) filter materially improves risk-adjusted returns. Diversify regime filters for the secret sauce.

In summary: Radge’s core philosophical tenets

• The trend is your friend—because of skew. You don’t need to “be right a lot;” you need to win big when you are and lose small when you aren’t. Markets aren’t normally distributed; momentum and trend-following exploit the real-world right tail.

• Trends can’t not happen. For trends not to exist, every asset would have to be perfectly priced and humans perfectly rational. That’s not our universe. So build to capture trends when they appear and to survive when they don’t.

Wrap Up

The pro vs amateur divide, per Nick: pros ride the drawdowns and are present for the next outlier. They profit from human bias—fear, greed, crowding—by refusing to trust their own emotions and by outsourcing discretion to rules they can defend under pressure. Write the plan. Build the engines. Diversify the return streams. Rebuke complexity. Then let compounding do its weird, beautiful work.

Hope that helps!

Simon

Get in Touch with Nick

Website

X

Linked In

It has been awesome producing the podcast, and I truly appreciate every one of you being along for the ride. Well, I’ve decided to step it up a gear or two!

As much as I love the trading, and I do very much continue to trade my own portfolio, the whole business of learning from others and working collaboratively with market gurus has really been more fun, more inspiring and better for my trading than I could ever have imagined. So, I’m doubling down on Algo Advantage to do more, way more!

A new website, a bold roadmap, and courses taught by real market wizards & quant fund managers. Watch the 10-minute back-story about my journey and how all this came together!

It’s right here on the home page on the sexy new site (scroll down a bit):

My Thoughts on Trading Success

We’re gearing up to launch:

• Courses led by genuine market wizards and quant fund managers

• Community for serious system-builders

• Software and research tools to accelerate strategy design

• Plus exclusive content, strategy workshops, live courses with quant wizards, meet-ups, and so much more…

To be clear: courses and community aren’t open yet. I couldn’t wait to share what’s coming, point you to the new site, and show you the short video that explains the vision. We’ll be launching very soon!

👉 Visit the site: www.algoadvantage.io
🎥 Watch the video: Right there on the home page

This approach is unusually unique!: instruction from practitioners who actually run money. Yep, that’s the bar.

So I’ve simplified the name & domain down to ‘Algo Advantage’ but will keep the Newsletter & Podcast as ‘The Algorithmic Advantage’. Apart from the podcast there will soon be:

• Algo Collective

• Algo Academy

• Algo Terminal

• Algo Architect

I did say this was HUGE. : )

More details soon. For now, check out the site and the video so you’re up to speed.

— Simon
The Algorithmic Advantage

P.S. Hit me up with what you most want in courses or community. It helps shape the launch order. Email me at info@algoadvantage.io

Jump to the site and video:

My Thoughts on Trading Success

First, let me tell you there are some very exciting things happening behind the scenes at The Algorithmic Advantage. We’re soon going to be launching community and courses, so watch out for an introductory email (and video) real soon. This is the first podcast where the ‘secret sauce conversation’ right at the end is reserved for members. Sit tight, when things are ready to go, you’ll be the first to hear. Trust me, it’s big. : )

Second, if you’re in London on the 14th-15th of October 2025 then the Quant Strats conference is the premier quant trading event in Europe this year, with over 600 quants, managers and the like getting together for some very interesting discussions, workshops and networking.

I’ve got you 10% off, just use the coupon code ALGOADVANTAGE10. Here’s the link:

https://www.alphaevents.com/events-quantstratsuk

With that out of the way, I spoke to Brent Penfold this week and was pleasantly surprised to hear about how his very old and very robust strategies continue to perform so well, with so little effort. This is encouraging for all! I mean, if simple can do it, why complicate!? Doesn’t mean it’s ‘easy’, but nothing worthwhile is.

In the age of machine learning, high-frequency trading, AI, untold data options and black box models, it’s easy to believe that only the most sophisticated strategies have any edge left. Yet Brent Penfold, veteran Australian trader and author of The Universal Principles of Successful Trading and The Universal Tactics of Successful Trend Trading, has spent decades proving the opposite. Yes, he has the track record to prove it.

His conclusion? Old, simple rules — the kind that could be written on a napkin — still work. They work not because markets are static, but because they are built on timeless principles of human behaviour, risk, and trend. Penfold calls these the “universal principles,” and they are the scaffolding behind every robust trading approach.

The magic is not in finding a perfect formula. It’s in building a disciplined process around a handful of simple, durable ideas that generate robustness. Let’s explore those six principles, with Penfold’s insights — and see how caveman-simple rules still stand tall in a modern quantitative portfolio.

Principle One: Preparation — Build Your Scaffolding Before You Trade

Every building stands or falls on its foundations. Trading is no different. Preparation means designing your rules for survival before you place a single trade.

Expect “maximum adversity and randomness.” Your job is not to avoid losses, but to become the “best loser” in the room — the one who takes small, controlled losses and lives to fight another day.

Brent urges traders to set boundaries before they start:

• A maximum amount they are willing to lose over their career.

• A risk management framework (position sizing, capital at risk).

• A partner or accountability mechanism to enforce discipline.

That last one we all tend to overlook right? Think we’ve got it covered. If I could go back and find a way to do this earlier, I’d do it in a heartbeat. These basics are easy to overlook, but this isn’t ‘fluff’, this is wisdom looking back and giving good advice.

Principle Two: Enlightenment — Survival First, Edge Second

The second principle is all about perspective. Enlightenment in trading means realizing that the first goal is survival, not riches. Be a blue-collar trader! The risk of ruin — the chance of blowing up — must be driven down to negligible levels before you worry about performance.

Once survival is locked in, the next step is to understand expectancy. Expectancy is the simple math that describes your edge:

(Average Win × Win Rate) – (Average Loss × Loss Rate)

Now I don’t believe a positive expectancy is some kind of holy grail – it’s still just a statistic you pulled from a back-test, but the principle is that you should set some clear thinking about your position sizing and hoped-for expectancy because combined, they will give you a pretty good idea of your ‘risk of ruin’. You want a 0% chance of ruin.

Penfold has shown that strategies dating back nearly a century — Gartley’s 3/6-week crossover from 1935, Donchian’s Four-Week Rule from 1960, and the Dreyfus 52-Week Rule — still generate profits across diverse markets when applied with discipline. What makes them powerful is not their elegance, but their robustness. He tested them across a 24-market futures portfolio with the same parameters, and they still delivered.

That robustness builds belief. And belief matters, because when your system inevitably hits a drawdown, only deep conviction in its expectancy will stop you from abandoning it at the worst possible time.

Survival, then expectancy. Enlightenment is seeing the hierarchy clearly.

Principle Three: Trading Style — Find Your Mode

Once you’ve secured survival and built belief, the next principle is choosing your style. Penfold makes the point that trading is a business and you have to do ‘what works’, not just what you feel like. However, you’ll still find your niche. When it comes to strategy construction, you’ve got to know the style and attributes of the model you are building in order to set the right expectations and judge it properly.

Trend following strategies follow different rules, have different needs, will perform at different times than mean reversion strategies. You’ll concentrate on different ratios and principles in the back-tests, and you’ll focus on avoiding the risks specific to each in different ways.

Principle Four: Markets — Fish Where the Risk is Lowest

Many traders obsess about finding the right pattern. Penfold insists you first choose the right waters to fish in.

Markets differ not just in opportunity but in risk. The best hunting grounds share these traits:

• Deep liquidity

• Transparency and fair regulation

• Low transaction costs

• The ability to short easily

• Round-the-clock pricing

Index futures and currency futures tick most of those boxes, which is why they form the backbone of Penfold’s preferred portfolio.

But the real insight here is portfolio thinking again. Penfold built a “P24” portfolio of 24 global futures contracts across sectors: equity indices, interest rates, currencies, energies, metals, grains, and meats. He applies the same simple rules across all of them.

By doing so, he transforms simplicity into power. Portfolio diversification is not an afterthought; it is the multiplier that makes simple work.

Principle Five: The Three Pillars — Money, Method, Mind

If there’s a heartbeat in Penfold’s framework, it’s this:

1. Money management comes first. Without capital, you can’t play the game. Position sizing is more important than entry logic. Fixed-fractional risk rules (say, risking 0.25–0.5% of equity per trade) are a trader’s lifeline.

2. Methodology comes second. Your system is important, but position sizing and discipline will be the factors that make or break you.

3. Psychology comes third. Even robust systems will test your patience. Hope, fear, greed, and pain are managed not by willpower but by systems: equity-curve stops, monthly reviews, and pre-planned rules.

Penfold makes clear that risk management sits at the portfolio level, not just the system level. His sizing logic ensures that correlated positions don’t sneak in disguised as diversification. This keeps his capital spread across truly independent bets.

The lesson is simple but severe: if you’re risking too much, or risking on correlated ideas, you’re breaking the first pillar — and no clever method can save you.

Principle Six: Trading — Execute, Then Get Out of the Way

Finally comes the act of trading itself. Penfold treats execution as a ritual. It sounds mechanical because it should be. Execution is not the time for creativity or improvisation.

By the time a signal appears, all the heavy lifting has already been done — in preparation, in risk management, in system design. Trading, ironically, is the least glamorous part of trading. It is simply pressing the button and moving on.

Robustness Testing

Here’s where Penfold stands apart from most shorter-term futures traders although he is in line with the likes of our classic trend following friends like Moritz Seibert and Jerry Parker: he only trades strategies which apply across all (or many) futures markets. That is, he isn’t interested in trading strategies that only work on the S&P for example. Unless a strategy is essentially universal enough to work on almost any market he throws it at, he discards it. Side-note: to be fair, Brent isn’t trading intra-day bars like other traders I’ve spoken to who prefer to build per-market strategies.

Think of the advantages here:

• The evidence of robustness is basically as obvious as a slap in the face.

• You get way more data to work on – you can build the strategy on all the data for a particular contract, and every other market is all out-of-sample data ready for testing.

• You get a robustness-test that is highly significant: “if it works on other markets, it’s robust, if not, it isn’t”.

Portfolio Level Thinking — The Curious Non-Standard Edge

To master systematic trading it’s incredibly important to build individual strategies with the portfolio in mind. There will be rules for the strategy and rules for the portfolio.

One curious, non-standard portfolio rule Brent has is that if two systems generate a signal on the same day for the same market, he only takes one trade. This runs counter to conventional thinking in that he’s manipulating the individual model by potentially skipping trades. The catch is that he already knows this is how he’ll run his portfolio, so he’s building strategies highly unlikely to trade on the same day in the first place.

This subtle twist has big implications. It means that when designing individual strategies, you must consider how they will behave together. It forces you to ask: “What happens when these signals overlap? Am I truly diversified, or am I just rephrasing the same idea?”

It also leads to robustness testing at the portfolio level, not just at the strategy level. A system that looks good in isolation may add no value — or even add risk — when combined with others. Portfolio-level robustness testing ensures the mix of systems is stronger than the sum of its parts.

This way of thinking demands more of the trader, but it produces a sturdier framework. It is one of the quiet hallmarks of Penfold’s design process.

Have Markets Changed?

The natural objection to running these ‘old simple strategies’ is that markets are different now.

However, Penfold reminds us that the principles of markets have not changed. Human behaviours — fear, greed, herding, confirmation bias, etc. — are as old as the markets themselves. The earliest trend followers, from David Ricardo in the 1800s to Richard Donchian in the 1960s, all leaned on the same maxims: cut losses, let profits run, follow the flow.

Markets evolve, but the universal attributes endure. That is why simple rules continue to work when applied across many markets with discipline. What fails is curve-fitting — the urge to mine the last five years of data for a pattern that will vanish tomorrow.

In other words, the future is uncertain, but the universal principles are timeless.

Diversify, Diversify, Diversify

Another aspect of Penfold’s portfolio level thinking is that traders should seek to add new markets and new models, not simply increase size on existing ones.

The temptation when a strategy is working is to scale it up aggressively. But this concentrates risk instead of spreading it. A far safer path is to add genuinely uncorrelated markets (currencies, rates, commodities, indices) or to add different styles (trend and mean reversion) that dance to different rhythms.

Diversification is the only “free lunch” in trading. And as Penfold shows with his P24 portfolio, it transforms simple rules into durable performers. One system on one market is a curiosity. That same system, applied across a global portfolio, becomes a resilient edge.

Diversification by market and method is how traders survive the long run.

Five Takeaways for Traders

1. Simple still works. Don’t dismiss an old breakout rule because it looks primitive. Simplicity often equals robustness.

2. Portfolio thinking matters. A lot happens at the portfolio level. Risks change, capital allocation rules are needed, diversification becomes real.

3. Diversify by method as well as market. Blend models, markets, time-frames to reduce correlation.

4. Robustness beats cleverness. Try multi-market testing as a robustness-test. How much are you prepared to bank on the idiosyncrasies of a specific market?

5. Principles don’t age. Risk management, good process, disciplined execution and right expectations probably matter more than any indicator.

Get in touch with Brent

www.indextrader.com.au

There’s a special place in trading graveyards reserved for the back-test that looked gorgeous on paper and then detonated in production. I’ve been there. If you trade long enough, you will too. We all know the over-fittings issues, and I’ll get into that, but there’s another reason why back-tests can fail: the initial purpose is not matched to the right method. If we ask the wrong thing of the test, measure it with the wrong yardstick, or ignore how strategies behave when they’re combined (not consider portfolio impact), then failure is likely. Laurens Bensdorp has a major focus on this – nicely summarised as building strategies with purpose.

The punchline is simple: your objective should dictate everything—what you build, which metrics you care about, and how you size and combine the pieces. Or as Rich Brennan puts it succinctly in his fantastic recent appearance on Episode 361 of Top Traders Unplugged, “your objective dictates your design.”

1) Start with purpose, not with code

Most back-tests fail ex post because they were optimized for the wrong mission ex ante. Using trend following as an example, Rich breaks managers down into four archetypes that behave—and should be judged—very differently: replicators, core diversifiers, crisis risk offset managers, and outlier hunters. If you’re replicating the SG CTA index, tracking error probably matters more than headline Sharpe. If you’re a core diversifier inside a multi-asset book, focus on portfolio-level Sharpe and correlation. Crisis-risk offsets live or die on convexity during selloffs. Outlier hunters care about payoff asymmetry, skewness, and top-trade contribution, not whether the equity curve is smooth this quarter. The professor is bang-on as usual.

That framing changes design choices you’d otherwise debate forever on Twitter: breadth vs concentration; absolute momentum vs cross-sectional momentum; volatility targeting vs static small bets; symmetry vs asymmetry in rules. There is no universal “right.” There’s only right for your purpose.

For the retail trader I think the temptation is to believe that the only objective is high returns with minimal drawdowns, aka smooth equity curves. But as Laurens brings out, once you have strategy 1, the purpose and reason behind strategy 2 will begin to be refined. Naturally, you’ll want something different. As we also brought out in our chat, the things you are looking for and the way you think, measure and build one kind of strategy (like mean-reversion), will be completely different to how you’ll build another (like trend-following). To measure them by the same yardstick or to assume similar risks, will simply not work. Trying to build a trend strategy with a 70% win rate means, by definition, you’ll cut off the positive outliers that are otherwise expected to do all the heavy lifting in this kind of strategy.

As an example, if you are hunting fat tails, cutting exposure just as volatility explodes “clips the wings of [your] biggest winners.” As Rich says, “I want to ride the wave in full,” which is why he normalizes at entry and then leaves positions alone. Or another great example he raised is that if your edge comes from catching rare, explosive moves, maximum feasible breadth isn’t decoration—“it’s a core operating principle.” The cost of missing the one market that goes parabolic far outweighs years of mediocrity elsewhere.

Practical takeaway: Before you sit down to code, write down (a) the role this strategy must play in the portfolio, and (b) the metrics that best capture success in that role. Then build to those metrics and stop optimizing once the design meets them.

2) Ugly equity curves can be beautiful (in the right portfolio)

One costly back-test biases is fetishizing pretty equity curves. Laurens Bensdorp makes the opposite case: be willing to add a strategy with an ugly equity curve or even a negative standalone return if it fills a structural hole in your book (like hedging catastrophic failures). Most traders won’t do it precisely because it looks ugly—and that’s your edge.

Think hedging, long-vol, short-equity overlays—deliberately lossy in the median state of the world, but explosive when you need it. In his discussion with me on the show, Laurens points out that a long-vol component can “dramatically improve the overall result of your portfolio” when the long-only equity sleeve gets hit in lockstep. He even sketches a concrete long-vol rule using something like VXX with a breakout filter (e.g., a Keltner/ATR trigger).

If your objective includes insurance, then the metric shifts. Instead of “highest CAGR,” think “portfolio MAR during equity drawdowns,” “crisis convexity,” or “time to recovery.” Judge the hedge by its portfolio contribution on your worst 5% days, not by its solo back-test. You’ll stop throwing away “ugly” curves that are doing exactly what you hired them to do. Don’t fear – the excitement is still there: in your overall portfolio result, compounding your equity more efficiently and especially during chaos when others are suffering. Be wary of ignoring it just because you ignored it on the first run of your backtest. Don’t be a gambler.

Practical check: In every strategy review, include a sheet titled “Why this looks bad alone but strong together” and show: (1) correlation to the core sleeve in stress windows, (2) contribution to worst-day P&L, (3) improvement in peak-to-trough and time-to-recovery at the portfolio level.

3) Parrondo’s paradox: when two losers make a winner

In game-theory terms, Parrondo’s Paradox is seen when “a combination of losing strategies can become a winning strategy.” (Wikipedia) The finance literature shows that the mechanism can be mundane: diversification and switching rules can create favorable drift when payoffs are path-dependent. (Michael Stutzer’s work is a good starting point if you want a gentle, finance-flavored derivation.) (Leeds Faculty)

This isn’t magic; it’s interaction. The visual in the video interview was awesome: two descending “staircases” (two losing processes). Combine them, and the ball rises—the composite path drifts up because the patterns of wins and losses interleave favorably. That’s Parrondo in a nutshell, and it’s why we should obsess over how we combine strategies, not just over each strategy in isolation.

Where do traders go wrong?

• They select only “individually great” systems, unknowingly correlating the failure modes.

• They allocate capital by recent Sharpe, which often synchronizes the book of strategies—great right up to the regime break. Heed the warning of LTCM.

• They never test allocation heuristics (equal risk, individual stock exposure, dynamic strategy allocation, static small bets, etc) as design choices in their own right.

4) Beware the seduction of pretty curves (over-fitting 101)

There’s an art to applying the science, Laurens mentioned. A strict set of rules for how to build and robustness-test a strategy is great, however one must know there will be different principles and methods at play for different strategies. Without understanding this you can end up overfitting to the noise rather than extracting an enduring signal.

Three practical anti-overfit policies could include:

1. Design-first, then test. Write down the mechanism you expect to harvest (trend persistence, mean reversion after liquidity shocks, term-structure convexity, etc.) before you see results. The design-first logic specifically helps to avoid the data-mining trap. Think about the trade-by-trade results (not the overall portfolio) and consider the importance of trade sequence to your particular model. In essence, do more analysis and less pressing the optimize button.

2. Simplicity beats cleverness (multiplied). Laurens calls it “multiplying simplicity”: build simple strategies with few parameters that are fundamentally different from each other, and let the combination do the “complex” work of smoothing the path.

3. Use the right robustness tools for the right style. Methods that reduce overfitting in convergent models (e.g., some Monte Carlo treatments) might not transfer cleanly to trend following (divergent models), where outliers are irregular and non-repeating. That’s one reason they argue trend followers could even use the full dataset judiciously instead of carving out conventional out-of-sample windows—because you don’t want to throw away your scarce tail events. (You can disagree with the prescription; the point is to align the validation method with the strategy’s signal ecology.)

Once the purpose is set, you can still follow various statistical principles:

• Too many degrees of freedom per trade. If your parameter count rivals your annual trade count, you’re fitting noise!

• Narrow regime dependence. All the edge comes from two crisis months? Assume it won’t repeat the same way.

• No cross-market validity. If it only works on one contract but dies on close substitutes, it isn’t a robust process—it’s historical happenstance.

• Optimization without budget. If you don’t cap how many knobs you’re allowed to tune (or how much improvement you’re willing to believe), you will inadvertently optimize on luck.

Another Trend Following Example from the Professor

In that TTU episode (361) Rich ran an interesting experiment: equal-weight a 68-market outlier-hunting portfolio with no hindsight and you get a respectable MAR ≈ 0.8 despite 27 unprofitable markets in-sample. Now randomly pick 300 different 30-market subsets from the same universe: only ~12% match or beat that MAR; median outcomes fall well below 0.5, with many survivability-threatening results at the lower quartile—purely because the 30 markets selected were not as lucky. 68 markets means more chance of catching the big trend, if that’s your objective.

So if you’re an outlier hunter: the very thing that makes your edge (fat-tail capture) also makes your realized performance highly path-dependent in finite samples. The antidote is obvious but operationally hard: more hooks in the water (trade more markets)—even if some markets look “quirky,” even if many contribute nothing for years—because one fat tail pays for their keep.

The Sharpe ratio isn’t going to capture this important metric and tell you “Sorry, you didn’t trade enough markets”, so Sharpe isn’t the thing you should be concerned about in this scenario. Your objective function should be married to your actual objectives; in this case, be open to opportunities wherever they may occur and hang on for dear life when they happen. This is going to preclude a fixation on “minimizing drawdown”. Starting to make sense?

Practical implications:

Don’t compare all strategies with the same metrics. Individual equity curves aren’t for ego trips, focus on the portfolio. Consider the archetype of your strategy and build, measure, test appropriately. To quote Rich again, lining up a bus, a sports car, and a motorbike, then ranking them on a racetrack lap time, is misleading. Ask “right for what objective?” first.

5) Building a purpose-first validation workflow

Here’s a possible check list you could use to ensure more trust in back-tests:

1. Clarify objective & metrics

• Strategy Type / Archetype: What are we going for? What are the implications for things like trade count, commission drag, markets it should run on, where profits will be derived, what risks are present.

• Primary metrics: If it’s a hedge strategy, well, how did it do in the crises obviously. If it’s a trend strategy we might be looking at skew, top-decile trade contribution, time under water, etc. If it’s a reversion strategy, I’m interested in individual trade payoff, win rate, clustering of trades, concentration risk, exposure during black swan events, etc. Align metrics to your mission.

1. Design first, then code

• Document the economic/structural/behavioral logic the rule exploits.

• List assumptions that must hold (microstructure, liquidity, regime features).

• Specify when you expect the strategy to make money, and when it shouldn’t, before you see results. You shouldn’t be optimising parameters for the sake of it (max return say), but to identify vulnerabilities and make design choices that address these potholes.

1. Right-sized simplicity

• Enforce a parameter budget (e.g., ≤3 tunables per entry/exit complex). Simplicity scales.

• Favor orthogonal simple rules over one complex rule (“multiply simplicity,” as Laurens says). “If you do that in a logical way where you understand what the weakness is… you increase the risk adjusted return,” he said. In other words, embrace simple models but combine them thoughtfully.

• If you are analysing the data for signals, rather than pushing it to deliver a ready-made strategy in a few steps, you will naturally be less prone to over-fitting because you are taking a ‘research-first’ approach. Good strategies exhibit plateaus in parameter space – broad regions where performance is relatively stable. The key is humility. A back test is a model of the past, not a prediction.

1. Robustness testing matched to strategy

• For trend-following where signals are sparse and outliers irregular, prefer multi-market, multi-decade testing and perturbations (slippage shocks, delay entries, skip signals) over carving away scarce tails for OOS. The OOS data won’t be long enough to measure success.

• For convergent or shorter-term styles, walk-forward, out of sample and alternative market tests might be a lot more useful. Monte-carlo tests which shuffle trade results are likely to only make things look safer than they are, because the risk for reversion traders is the synchronisation of trades during tail events! What’s the ‘crisis score’?

• Expanding breadth (number of markets, strategies, non-correlated payoffs) is always beneficial. An ounce more breadth is worth far outweighs individual strategy tweaks. Do you have metric for ‘breadth-health’?

• Pre-commit to acceptance criteria. Ensure logic reigns with parameter selection. Forget the best outcome, remember the worst. Be statistically minded, but know where your objectives will or won’t be captured by various metrics. Over-fitting can masquerade as statistical significance; don’t rely on code, press the logic.

1. Portfolio-aware evaluation

• Run strategy-in-portfolio simulations against your existing stack, measuring the role it’s meant to play (drawdown relief, convexity, skew). Does it add to the portfolio overall?

• Building orthogonal strategies, harvesting diversification, taking steps to better utilise and allocate capital are all free lunches that can compound returns without requiring you to be a better trader.

1. Luck accounting

• For trend traders, use top-trade concentration and luck-adjusted ranges to show yourself what happens if you miss the one fat tail (and with less breadth, odds rise that you will).

• For reversion traders, force tests to include the disastrous events that could have wiped the strategy out. Try to break it so that you’re not blind to the risks.

The point of the back-test is not to maximise an in-sample Sharpe; it is to reject fragile hypotheses. A robust research process deliberately tries to falsify its own ideas by exposing them to alternative samples, parameter perturbations and different market universes. Smooth curves are alluring; survivability is the edge.

Closing: Portfolio construction beats single-system cleverness

Back-tests fail because we treat them like verdicts rather than experiments. Be a better scientist. The remedy is to embed purpose at the centre of your design, judge sleeves by the role they play in the portfolio, and respect interaction effects that might even turn two losers into a winner! Laurens’s advice here is gold—embrace the hedge that looks bad alone if it rescues the whole when it matters.

And above all, keep Rich’s mantra close: objective → design → metrics. When you get that chain right, back-tests are just a research tool. The goal is to generate profits, which will happen if you let the back-test speak, rather than torture it till it tells you what you want to hear.

We traders love to search for recurring patterns, but markets are complex adaptive systems influenced by countless variables. Patterns can rhyme, but they rarely repeat exactly. When it comes to statistical significance, breadth is your friend. Running a broad range of strategies and parameter settings at least places you in a position where some of those will do great next year. That’s an objective that has statistical and logical validity and will yield better results over time than gambling on the one or two that worked best last year. Treat every result as a draw from a distribution, not a prophecy, and you’ll set the mind into the right place for proper strategy development.

Be purposeful about your diversification.

Survive first, thrive later.

Hope that helps!

Simon

Get in Touch with Laurens

Website

X

Linked In

The Quantitative Journey: From Discretionary to Systematic

Cesar began his career trading mutual funds and individual stocks, influenced by William O'Neil’s Investor's Business Daily strategies. It was in the early 2000s that quant trading captivated him, especially due to his strong programming background. Tools like AmiBroker transformed his approach, making systematic testing accessible and scalable.

His professional breakthrough came at Connors Research, where he spent a decade deeply immersed in mean reversion and volatility strategies. “Working alongside Larry Connors,” Cesar reminisced, “was like drinking from a firehose of trading ideas.” This was where he first discovered the counterintuitive finding that mean reversion strategies performed best without stops.

Building a Robust Portfolio

Today, Cesar’s personal portfolio is diversified across several strategy types:

• Mean reversion: Targeting both long and short opportunities in universes such as the Russell 3000 and S&P 500.

• Breakouts: Primarily in small-cap stocks, harnessing their volatility.

• Momentum & Rotation: Utilizing ETFs like SPY, TLT, and NASDAQ-100 stocks.

• Volatility: Trading the VIX and SVIX, though acknowledging volatility strategies can be brutally hit-or-miss.

• Tactical Asset Allocation: A slower-paced, dual-momentum method for retirement accounts, focusing heavily on managing drawdowns.

“Now that retirement looms,” Cesar explained, “I’m less about shooting for the moon and more about cushioning my falls.” His tactical ETF strategy reflects this philosophy perfectly, keeping him in cash or stable assets during turbulent times.

Strategy Creation: Start with a Clear Goal

For Cesar, quant strategy design starts with well-defined objectives:

1. Identify the Universe: Whether it’s S&P 500 stocks or a broader range like the Russell 3000, clearly defining the universe in line with your objectives.

2. Set Return and Drawdown Expectations: Cesar sets realistic goals—for example, aiming for high-teens returns with manageable drawdowns in short strategies.

3. Define the Trading Style: Short-term holds, momentum, or breakout—each style dictates its own rules and parameters.

This targeted approach prevents the trap of endless parameter tweaking and over-fitting.

Testing Robustness and Avoiding Overfitting

We got a few insights into the robustness testing methods Cezar uses:

• Parameter Sensitivity Testing: Cesar adjusts parameters by 10-20% around his base values, performing thousands of runs. He then calculates averages and standard deviations to gauge robustness.

• Standard Deviation Checks: If the selected parameter set is significantly outside one standard deviation from the average, it’s likely overfit, warranting reconsideration.

Deciding When to Retire a Strategy

One major quant trading challenge is knowing when to pull the plug on underperforming strategies. Cesar elegantly sidesteps subjective judgments by employing a rotation system:

• Portfolio Ranking: He maintains around ten strategies, ranking them monthly or quarterly based on recent performance.

• Top Performers Only: The top five strategies earn their place in the live portfolio. Poor performers rotate out.

This methodical, evidence-driven approach removes emotional bias. If a strategy fails to make it back into rotation for a year or two, Cesar gracefully retires it. "Strategies don't usually die dramatically; they slowly fade away," he noted wryly.

Is It Getting Harder to Find Profitable Strategies?

Absolutely, according to Cesar. Competition and efficiency continue to escalate. Edges become thinner, and strategies' shelf lives shrink. To combat this, Cesar emphasizes diversification and continual innovation, regularly revisiting strategy ideas and adjusting approaches. He doesn't necessarily hold a conviction that just because something worked in the distant past, it will work in today's market. There are implications for in sample / out of sample testing. This also highlights why he has chosen a rotational / dynamic approach to strategy deployment - only keeping high-performance strategies in the live portfolio.

Combining Strategies: Zen and the Art of Diversification

Managing multiple strategies requires a careful balancing act. Cesar avoids heavy correlation by blending different styles—mean reversion, breakout, momentum, and volatility. He also uses a rotation mechanism to manage correlation dynamically, ensuring a stable and robust portfolio performance. I did fail to ask one question, which I should have: 'When you sub-off a strategy and sub-another in, do you swap it with a 'like' strategy?". Meaning, I think it would be interesting if you could sub strategies in and out, while still maintaining desired correlation and strategy-type exposures!

Amibroker vs. RealTest: Quant Trading Tools

When discussing software, Cesar praised both AmiBroker and RealTest, but noted clear distinctions:

• AmiBroker: Highly flexible, and nearly anything can be custom coded. This makes it suitable intraday or options strategies.

• RealTest: User-friendly, does multi-strategy trading which Amibroker simply doesn't do, is incredible fast and can handle almost anything you can throw at it. However, doesn't yet to intra-day strategies or options. Some flexibility may be lost for certain customizations.

Practical Tips for Effective Mean Reversion Trading

Mean reversion is Cesar’s bread-and-butter. I couldn't resist asking for some insights from the MR Master:

• Focus on exits and ranking, not just entries. I can attest to that.

• Constantly refine: Keep exploring new ideas, as markets evolve rapidly.

• Review execution regularly: Ensure backtested results match real-world performance closely.

Closing Thoughts

In Cesar’s words, "Quantitative trading isn’t just about being smart—it’s about being methodically and systematically smarter." Given how markets evolve, staying systematically smarter is more crucial than ever. Loved his dynamic portfolio adjustments, I'm going to explore that further!

Let me know if you have any comments or questions!

Trade Well & Prosper,

Simon

Get in Touch with Cesar

Website

X

Linked In

Getting Started: Beyond Buy-and-Hold
One of the first questions I asked Pavel was how passive crypto investors could evolve into more active, strategic traders. His advice was blunt: "crypto asset class is really for trading," not just buying and holding. While long-term investments like Bitcoin or Ethereum might still be viable, Pavel stresses crypto's volatility and inefficiencies are far better suited to active trading strategies.

For newcomers, Pavel recommended a straightforward approach—trend-following strategies focused exclusively on the top 10-20 coins by market cap to capture longer-term movements without being swept up in pump-and-dump volatility common in smaller altcoins.

Understanding the Crypto Ecosystem
Diving deeper into crypto trading means grasping basics like wallets, crypto transfers, and understanding some of the big picture risks in the space (not only can a coin go to zero, but an exchange can collapse overnight). Pavel simplified this by recommending crypto futures trading due to significantly higher liquidity (3 to 10 times greater than spot markets) and lower trading costs. He also emphasized maintaining multiple accounts across exchanges to mitigate platform risks, a crucial insight following events like the FTX collapse.

Tackling Data Scarcity
Historical data scarcity in crypto poses challenges for quantitative model-building. Pavel underscored the importance of sourcing survivorship-bias-free data, typically from major exchanges like Binance, Bybit, and OKX. His team meticulously cleans this data, ensuring delisted coins remain included to preserve the integrity of the backtests. There are some other data sources around, a couple that come to mind include Brave New Coin, CoinAPI.io, Polygon.io and there are even free sources.

Given the limited data, Pavel recommends cross-validation with strategies developed from commodities and stock markets, particularly referencing the tech stock volatility of the late 1990s and early 2000s as analogous historical periods useful for crypto modelling.

Robust Strategy Design
Pavel’s approach to strategy creation focuses on simplicity and robustness, limiting conditions to two to four per strategy. Each model is built initially for traditional assets and then adapted minimally for crypto by adjusting primarily the exit conditions, catering to crypto’s unique volatility.

His trading stack is comprehensive, utilizing around 15-20 models running simultaneously, each targeting different market dynamics, from short-term momentum to longer-term trends, and from mean reversion to strategic hedging positions.

Combining Models for Hedging
Combining these different strategy types, such as mean reversion and momentum, can substantially enhance portfolio robustness. Short-term mean reversion shorts complement long-term momentum longs to reduce drawdowns, effectively balancing exposure across market cycles. Then there are models which seek to capture pull-backs, but ride them. Pavel describes this interplay of mean reversion and trend following as capturing the "best of both worlds."

Managing Risks
Risk management emerged as a key discussion point. Pavel & I both have learned hard lessons from the volatility of crypto, particularly the catastrophic declines seen in coins like Luna. To handle this, Pavel maintains very small position sizes (0.5-3% per position), spreading exposure across numerous strategies and exchanges.

Additionally, Pavel avoids hard stop-losses due to crypto’s erratic price action, instead managing risks through portfolio diversification and strategic hedging.

Tech Stack & Infrastructure
Behind Pavel’s strategies lies sophisticated infrastructure. Running multiple models 24/7 requires comprehensive automation—cloud-based trading platforms, continuous monitoring, and robust API integrations with exchanges. That said, it's not difficult to get started with a simple stack, contact me if you want to know more about the options, but there are tools out there that will handle it. The key however is that if you want to take full advantage of crypto, with the lowest possible risk, you're going to want to trade algorithmically and automate: so that you can handle a larger number of strategies and assets, keeping exposures low and alphas diversified.

If you're ready to embrace the volatility, the crypto market holds enormous potential, provided you manage your risks meticulously and combine strategies intelligently - as the outstanding performance at Robuxio evidences all too well!

Trade well and prosper!

Simon

Get in touch with Pavel & the Robuxio team

X:

Linked In:

Website:

Psychology for Quant Traders? Really?

Quantitative futures traders like to think in code, not clichés—but Dr Brett Steenbarger makes a compelling case that mindset is part of the edge. In this interview, Brett argues that the same statistical rigor quants apply to markets should be applied to the grey matter behind the keyboard. Here's a guide for the advanced systematic trader who suspects “psy-stuff” might be more than motivational posters.

Born Vs. Made—The Talent + Skill Equation

I opened with the turtle-era debate: are great traders wired or trained? Brett’s answer is happily Bayesian. Yes, people arrive with innate “attentional talents” (think of the chess prodigy who can see five moves ahead), but sustainable P/L comes only after domain-specific skills are layered on top—just as a natural sprinter must still learn baton hand-offs to win a relay .

Practical take-away for futures quants:

1. Run a brutally honest post-mortem of which research tasks energise you—data-wrangling, model design, risk routing—and double down on those shards of talent.

2. Outsource or automate the chores that drain you; you can’t debug code while wishing you were exploring yield-curve regimes.

Different Brains, Different Horizons

Brett contrasts three archetypes:

The quant generally sits in the 'slow thinking' space (a reference to Daniel Kahneman's book "Thinking, Fast and Slow"), taking time to generate ideas. However, in this big-picture context there can still be fast feedback loops once live trading, so it does pay to trade a style that will work for you once you go live. Knowing which stressor prowls your niche lets you build the right mental armor. Usually it takes some exploration and experience to really hone in on what suits you.

Creativity: The Missing Factor in Sharpe Ratios

When “all you have is a hammer, everything looks like a nail,” Brett quips. Alpha today is less about raw processing power than seeing the familiar differently. His example is Marcos López de Prado’s use of event-time bars—each bar formed after a fixed number of contracts—not clock-time bars (tick charts?). That reframes the entire statistical structure of price series and reveals fresh cyclical signals.

Rapid-fire creativity drills for algo teams

• White-board mash-ups – every researcher posts their top 3 ideas; the room brainstorms what the world would look like if all 15 were simultaneously true.

• Cross-pollination meetings – pair the FX gal with the rates guy to hypothesise regime triggers that flip systems on/off.

• Daily “one weird plot” ritual – each coder brings a chart of something nobody tracks (distance-to-VWAP at settlement?) and defends why it might matter.

Creativity isn’t mystical; it’s a process measurable in research throughput.

On a more personal level, I know that my extreme businesses can stifle my creativity. It's usually on our day-off, sitting under an apple tree, that the big ideas come. Perhaps creativity married with statistical rigor and intellectual honesty (being honest about when you are over fitting, or have a less-than-scientific method) are the keys to systematic trading success.

Overfitting, Context, and Turning Systems Off

Brett skewers the rookie obsession with the “Holy Grail system.” Institutional PMs, he notes, expect to toggle models in and out according to market context—say, an FX-momentum strategy that only trades when the yield-curve shape matches historical trending regimes. Robustness lives in breadth of conditional edges, not a single swiss-army knife .

Some Robustness Checklist items from Brett:

• Walk-forward across non-overlapping regimes to be sure a single regime isn't carrying the stats.

• Test on sufficient data.

• Kick the tyres: nudge entry, exit and sizing rules, swap data frequency, even change the market. If P&L falls off a cliff, the edge wasn't real.

• Don't data mine; demand and economic or behavioural rationale first.

• Edges often appear only in specific volatility, liquidity or rate regimes; build regime filters and be willing to turn systems off.

• He points non-programmers to Trading Blox, Trade-Ideas Odds-Maker and Worden Blocks so nobody has an excuse to skip testing. Get Real Test and you can become a programmer really fast.

• Stress-test with randomised events.

• Try to break it. This is gold.

• Shadow-trade in sim until the gut agrees with the statistics; intuition is an overfitting early-warning system.

Yes, even quant trading is art and science. There's an art to using the science correctly.

Trading as a Competitive Performance Sport

“Markets are a competitive activity,” Brett reminds us. Like athletes, traders need deliberate practice and state-control. His latest fascination is neuro-feedback: using a Muse headband to train the brain into sustained alpha-wave focus. Birds chirp in the app when concentration deepens—gamified mindfulness for quants .

Older school? Bio-feedback via heart-rate variability works too . The goal isn’t Zen serenity but selective arousal—full engagement without cognitive noise. Concentrated brains look different to simply relaxed brains.

Solution-Focused Reviews: Fix What Works

Typical “trading psychology” harps on mistakes. Brett flips the script with solution-focused coaching: catalogue the successes where you didn’t overfit or where you executed perfectly, then reverse-engineer those conditions and ritualise them. Build on strengths rather than obsess over flaws .

Action step: After each strategy creation project say, jot two things you crushed and one micro-tweak. Over weeks the wins compound; the tweak list stays small and actionable. As systematic traders we could apply this discipline to any number of work projects, such as reviews of our processes for robustness testing, etc.

Team Dynamics & Guarding the IP

Elite quant pods marry diverse specialists—data engineer, statistician, market-structure geek, portfolio orchestrator. Sharing raw P/L drivers outside the pod is taboo, but sharing frameworks (e.g., NYSE uptick/downtick ratio as an institutional footprint proxy) is kosher and sparks reciprocal insight. Having a team of collaborators is a tried and true scientific model. Most great discoveries are a result of multiple minds working together, standing on the shoulders of giants. I'm looking forward to developing a community here at the Algo Advantage, stay tuned for that.

Solo futures traders can mimic the model:

• Team up with someone you find on a forum interested in tackling the same problems as you.

• Meet weekly to brainstorm while redacting proprietary parameters if need be.

• Seek out a mentor.

Mentoring, Simulation, and Managing Expectations

Whether at SMB Capital or multi-strategy hedge funds, newcomers face the same progression: sim → tiny real money → scalable book. The structure safeguards capital and compresses feedback cycles. Retail quants should copy the path—trade micros, not minis, until the Monte Carlo of live results matches the back-test confidence interval .

Oh, and You Wanted to Know about Brett's own Trading?

Brett’s own trading is a deliberately narrow, high-conviction affair. He trades the E-mini S&P and other index futures off three volume-based charts (small, medium and large bars that form after a fixed number of contracts, not after a fixed number of seconds) so the market “breathes” at its natural pace rather than the clock’s. Across all three he layers adaptive moving averages, a short-lookback RSI, a detrended oscillator and—most crucially—an order-flow delta pane that tracks volume lifting the offer versus hitting the bid; when heavy selling can’t push price lower, he stalks the inevitable squeeze. A 15-second NYSE TICK then fine-tunes entries, and position size is dialled up only when the signals line up across every frame. To keep the mind as disciplined as the stats, he allows himself one A-plus trade in the morning and one in the afternoon—sniper fire rather than machine-gun bursts—before resetting and journaling for the next “mini trading day.”

Closing Bell

The punch-line from Brett’s research is simple: systematic trading is less “set-and-forget” and more Formula 1 pit-crew—engineering precision plus real-time human performance. Code finds edges; psychology keeps you creative enough to refresh them. Or, as one of Brett’s blog posts puts it, “We can’t run robust systems from brittle minds.” Not a bad mantra to stick on your trading monitor!

So glad I took the opportunity to talk with Brett, I got way more out of it than expected. Thanks Brett!

Get in Touch with Brett:

X

Linked In

Website

Books

Andrea Unger is actually a four-time World Trading Champion, and here he offers a comprehensive and structured approach to quantitative trading in futures markets, emphasizing practical methods for strategy design, robustness testing, portfolio construction, and system deployment.

Strategy Design Principles

Unger recommends starting strategy development with simple, robust ideas, such as breakout or reversal setups (e.g., buy yesterday's high breakout). The initial goal is to validate whether the strategy shows a basic statistical edge, focusing purely on system behavior without initially considering transaction costs.

He refines strategies by introducing context-based rules derived from historical market conditions. These conditions must be logically sound and market-related, not merely optimized parameters. For instance, strategies might incorporate rules based on volatility conditions or recent directional trends. Unger maintains a library of market patterns (e.g., performance after low volatility days), which he tends to use as setups rather than indicators.

Strategies are explicitly matched to market behavior—trend-following approaches for inherently trending markets like crude oil, counter-trend or mean-reversion strategies for typically mean-reverting markets like the E-mini S&P 500. Unger diversifies timeframes (intraday to multi-day) but cautions against expecting fractal behavior across timeframes, stressing that shorter timeframes are noisy, but can be used primarily to enhance entry precision rather than profitability.

Position Sizing and Risk Management

Position sizing follows conservative, fixed fractional risk principles, typically risking no more than 1% of account equity per trade based on worst-case historical losses or drawdowns. Unger emphasizes validating a strategy's average trade size first, ensuring it exceeds trading costs, before increasing leverage.

Portfolio comparisons normalize risk across strategies by adjusting contract sizes so each system risks roughly the same percentage per trade. Drawdown tolerance guides maximum permissible leverage rather than performance optimization alone, helping to manage the cumulative risk inherent in running multiple strategies simultaneously.

Robustness Testing and Validation

Unger employs rigorous in-sample/out-of-sample testing but typically avoids traditional walk-forward optimization due to the discrete, pattern-based nature of his systems. Instead, he uses parameter stability tests—small adjustments around chosen parameters—to ensure systems remain profitable and robust against minor variations in market conditions.

Additionally, Unger validates systems by perturbing historical price data slightly (randomized data tests), confirming that slight market data shifts don't significantly degrade performance. He prefers systems whose results remain stable across these variations rather than extreme outliers, thereby ensuring realistic robustness.
Systems showing excessively optimistic backtest results are critically re-examined to rule out data or methodological biases. He explicitly cautions against deceptive strategies tested on exotic charts (e.g., Renko), which might not realistically represent live trading conditions.

Strategy Diversification

Unger actively diversifies across approximately 30-40 liquid futures markets spanning equities, fixed income, currencies, energy, metals, and agriculture. Each market typically hosts multiple strategy types—trend-following, mean-reversion, breakout, and volatility-based methods—to ensure comprehensive market condition coverage.
Further diversification occurs through varied trading timeframes—short-term intraday (5 to 15-minute bars), medium-term (hourly), and daily bars—ensuring reduced dependency on single market behaviors or short-term volatility cycles.

Portfolio Construction

Unger employs two proprietary portfolio management tools (only available to his students)—Titan and Zeus—built on MATLAB for strategy selection, portfolio construction and risk management. Both tools systematically rank strategies by recent performance momentum, applying strict performance criteria (e.g., profitability over the last x months).

Zeus, if I understood correctly, considers practical correlations—evaluating simultaneous market exposure, actual trade overlap, and hedging effects. Zeus thus maximizes capital utilization, ensuring smaller accounts can optimally leverage micro-futures to achieve broader diversification without exceeding margin or risk limits. I think tools like this must be built by those taking this kind of trading seriously, given the likes of Trade Station and Multi Charts just can't handle it. Another option might simply be to save and then import equity curves into software like Amibroker or Real Test to analyse and optimize the portfolio of return streams in a systematic way. Mmmm that's worth thinking about actually, I'd be interested in hearing from you if you've tried that!

Like with Kevin Davey, monthly portfolio reviews dynamically rotate strategies, systematically replacing underperforming systems with better alternatives. Manual overrides occur sparingly, guided by strategic insights rather than short-term performance whims.

System Deployment and Maintenance

Unger transitioned from manual execution to full automation around 2010, significantly enhancing execution consistency and scalability. Automated strategies run continuously on a cloud server environment, minimizing manual errors and execution latency.

Continuous supervision ensures system integrity, focusing on monitoring for execution errors, order management issues, and ensuring strategy alignment with historical expectations. Intervention is minimal, and system adjustments are avoided during live trading to prevent reactive overfitting.

Strategies experiencing significant performance degradation are systematically retired rather than hastily "patched." Unger either entirely redevelops concepts in response to persistent market regime shifts or fully retires ineffective strategies. This disciplined lifecycle management ensures strategy integrity remains intact. I must admit, I'm beginning to like this theme of strategy rotation: I particularly like that poor performing strategies are automatically retiring themselves and there's no need to think about when to stop trading them.

Technology Stack

Unger’s technology infrastructure leverages MultiCharts for strategy development and execution, capitalizing on reliable historical data, backtesting accuracy, and robust live execution capabilities (with Interactive Brokers). MATLAB supports custom portfolio analysis, incorporating extensive matrix operations and strategy selection logic (Titan and Zeus tools). This environment allows rigorous, data-driven decision-making regarding strategy deployment and portfolio optimization.

A dedicated VPS/cloud server provides robust, continuous connectivity for executing automated strategies, ensuring low downtime and reliable execution. Rigorous version control and distinct testing and live environments protect strategy integrity, enabling systematic and disciplined trading operations.

Practical Takeaways for Quant Traders

• Begin strategies simply and enhance logically rather than through blind optimization.
• Position sizing must strictly control per-trade and cumulative risk, focusing on worst-case scenarios.
• Robustness tests should include both parameter stability checks and data perturbations to prevent overfitting.
• Diversification is crucial—across strategies, markets, and timeframes—to smooth performance and mitigate risks.
• Portfolio management should prioritize correlation management and dynamic strategy rotation based on systematic performance metrics.
• Full automation combined with disciplined supervision and minimal manual intervention is vital for consistency.
• Strategic "retirement" of failing strategies prevents portfolio degradation, with redevelopment preferred over reactive adjustments.

Following these structured guidelines offers quant traders a disciplined, robust framework for systematic futures trading, aligning real-world practicality with rigorous quantitative principles.

More over on the website

Stay curious!

Strategy Design Principles
Kevin’s strategy development process begins with clearly defined goals—establishing the desired return and acceptable drawdown before writing a single line of code. He has learned through trial and error that conflating objectives (e.g., maximizing return without regard for survivability) can lead to ruin. His workshop curricula cover these foundational steps, teaching traders to:
• Set realistic performance targets
• Design strategies around specific market behaviours, whether trend-following or mean-reverting
• Avoid over-optimization by preferring one comprehensive test over multiple iterative tweaks

Kevin stresses that the coding platform (TradeStation, Python, etc.) is secondary to the robustness of the methodology itself; traders must focus on building sound rules before seeking the perfect back-testing engine.

Walk Forward Analysis: Best Practices and Common Mistakes
Kevin distinguishes his approach from other practitioners by emphasizing a one-shot walk forward process: optimize over an “in-sample” period, test over an “out-of-sample” period, and never revisit the in-sample parameters. Repeated retesting qualifies as overfitting and undermines the validity of out-of-sample results. Key takeaways include:
• Single-pass testing: Conduct one optimization and one validation, resisting the urge to tweak parameters multiple times.
• Beware of “cluster analysis” traps: Some platforms (e.g., TradeStation’s early implementation) automatically scan parameter matrices to find a “sweet spot.” Validating that same sweet spot on identical data simply reaffirms the initial optimization, rather than offering genuine out-of-sample confirmation.
Through this disciplined framework, Kevin seeks to minimize the impact of data mining bias and ensure that performance metrics truly reflect a strategy’s forward-looking potential.

Robustness Testing Beyond Walk Forward
Beyond walk forward, Kevin employs several layers of synthetic and real-time validation to gauge strategy resilience:
1. Logic based models relying on understandable causation not machine learning
2. Monte Carlo simulations on equity curves to assess variability in returns and drawdowns across randomized sequences of trades.
3. Real-time paper trading (often for six to nine months) to confirm live market behaviour aligns with back-test projections.
4. Equity‐curve inspection: He examines curve shapes for alarming features (e.g., overly smooth or consistently linear growth) as signs of over-optimization.
Kevin acknowledges that no amount of robustness testing can eliminate all luck components in back-tests; instead, he focuses on understanding and quantifying the role of chance, then building portfolios to mitigate adverse outcomes.

Tech Stack and Automation Tools
Kevin’s core toolkit comprises:
• TradeStation for strategy coding and initial back-testing
• Multiwalk (a specialized walk forward add-on developed by a former student) for rapid batch testing across markets and parameter configurations (only available to Kevin's workshop students unfortunately)
• Excel/VBA for customized Monte Carlo simulations, cluster analyses, and portfolio-level data aggregation
While he concedes that Python and other programming environments offer powerful alternatives, Kevin prefers sticking with familiar platforms to avoid the distraction of constant tool development. His guiding philosophy: “Focus on strategy, not on building the back-testing engine.”

Portfolio Construction Process
Combining intraday futures strategies into a cohesive portfolio involves several sequential steps:
1. Correlation screening: Eliminate strategies with historically high inter-correlations, ensuring that each component contributes unique risk factors.
2. Preliminary selection: From a universe of ~200 strategies, rank candidates by recent performance trends and drawdown characteristics over rolling 6–12-month windows.
3. Sector-balanced diversification: Formulate a weight assignment rule (e.g., equal risk contribution) to allocate equal portions of the portfolio to 7 broad sectors (such as rates, equities, softs, metals, etc.)
4. Position sizing: Determine the exposure of individual strategies to ensure diversification and equal-risk allocation is maintained across the portfolio
5. Real-time pilot: Trade the proposed portfolio in live simulation to observe actual behaviour before full deployment.
This “one-and-done” philosophy in portfolio testing parallels his walk forward rules: avoid iterative tuning on the final test to preserve genuine out-of-sample validity.

Monthly Maintenance and Rebalancing
Kevin dedicates the final trading day of each month to portfolio review and rebalancing:
• Update performance metrics for all strategies in the library (~200 in total).
• Select top performers (typically 20–30 strategies) and drop underperformers, aiming for sector diversification—ideally seven market sectors at roughly 14.3% allocation each.
• Conduct Monte Carlo on the chosen set to estimate potential worst-case drawdowns and compare realized returns against simulated expectations.
• Re-optimize individual strategies: He typically has 20–40 strategies per month requiring parameter updates via walk forward, scheduling optimizations across trading days.
This disciplined cycle ensures that the portfolio remains attuned to evolving market dynamics without succumbing to short-term noise.

Risk Management and Psychological Preparedness
A recurring theme in Kevin’s methodology is the interplay between statistical rigor and emotional resilience:
• Drawdown acceptance: Traders often overestimate their drawdown tolerance; real-time experience reveals that technical ability dissipates under actual equity drops. Kevin advises sizing strategies to limit maximum drawdowns to levels half of one’s perceived comfort zone.
• Monitoring and supervision: Regulatory requirements demand active oversight of automated systems. Kevin cautions that overseeing too many strategies increases logistical burden—arguing for a “sweet spot” of 20–30 algos for manageability.
By intertwining quantitative controls with human oversight, he fosters longevity in trading careers rather than short-lived performance peaks.

Performance Benchmarks and Goals
Kevin benchmarks his goals against institutional players (e.g., commodity trading advisors tracked by Barclay’s Hedge):
• Proprietary funds: the best of the best typically average 10–20% annual returns with matching drawdowns; they regard a 1:1 return-to-drawdown ratio as prudent.
• Kevin’s personal target: 50% annual return with a maximum 25% drawdown, acknowledging that some years meet both criteria while others fall short. That's a pretty high expected draw down from my perspective.
• Extreme contest performance (100%+ returns) involves high leverage and unacceptable risk for long-term trading; such feats, while impressive, clash with sustainable risk thresholds.
These benchmarks guide strategy design, ensuring that return objectives align with survivability imperatives.

Conclusion
Kevin’s systematic approach melds rigorous quantitative testing with pragmatic risk management and monthly maintenance protocols. By enforcing single-pass optimizations, extensive real-time validation, and lean portfolio sizes, he constructs a robust trading framework designed for consistency and longevity. Advanced traders can draw from his workshop principles to refine strategy design, navigate common back-testing pitfalls, and build diversified, adaptive portfolios capable of weathering market uncertainties.

His expertise lies in trading futures on US exchanges like the CME and ICE, spanning all possible sectors (Kevin names seven). Kevin employs a variety of strategies, from intraday trades using minute bars (even unconventional bars e.g., 32-minute bars) to longer-term positions held for months using daily bars. His approach prioritizes diversification across sectors and time frames to manage risk effectively, as well as monthly strategy rotation to deploy the hottest performers for the current market environment. For advanced quantitative traders, Kevin’s methodology offers a blueprint for generating, testing, and implementing trading strategies with precision and resilience.

Defining Objectives and Generating Ideas

A robust trading process begins with clear objectives. Kevin emphasizes defining goals upfront—such as a target return-to-drawdown ratio—to guide strategy development and prevent overfitting. Without this, traders risk endlessly tweaking strategies to perfection, a trap that often leads to failure in live markets.

Idea generation is the next step, where Kevin casts a wide net. He explores technical indicators, candlestick patterns, statistical methods, and cautious data mining. While he tests a variety of concepts, he leans toward simpler, causal (logical) strategies, noting they often outperform complex ones in live trading. For instance, a basic breakout strategy might suffice, though it comes with larger drawdowns—a trade-off traders must accept. Kevin also favours longer-term strategies, as they offer a better signal-to-noise ratio, reducing the impact of market noise and costs like slippage. Initial testing is usually (but not always) conducted on small data subsets to refine ideas without compromising the full dataset’s integrity for later validation.

Validating Strategies with Walk-Forward Optimization

Walk-forward optimization is a pivotal step in Kevin’s validation process. This technique splits historical data into in-sample periods (for optimization) and out-of-sample periods (for testing), simulating real-time performance. The process “walks forward” through the data, ensuring each out-of-sample test reflects unseen conditions. Note we deep-dived walk forward in the prior episodes with Bob Pardo, the investor of the process. Crucially, Kevin insists on a one-shot test: once defined, the strategy is evaluated without adjustments. Tweaking based on results risks implicit overfitting, undermining the out-of-sample integrity. Success hinges on meeting predefined criteria, like the return-to-drawdown ratio, ensuring the strategy’s robustness for future performance.

Assessing Risk and Performance with Monte Carlo Simulations

Post-walk-forward testing, Kevin uses Monte Carlo simulations to assess a strategy’s risk and performance. By resampling trade results, this method generates a distribution of potential outcomes, revealing the range of returns and drawdowns. It’s a critical tool for aligning strategies with a trader’s risk tolerance and setting realistic expectations. For example, a strategy might show promise in backtests but reveal vulnerability to extreme losses under simulation. While not a crystal ball, Monte Carlo provides a probabilistic lens, enhancing decision-making for advanced traders navigating uncertain markets.

Incubating Strategies: The Live Market Test

The incubation period is Kevin’s ultimate robustness check. After passing walk-forward and Monte Carlo stages, strategies are monitored in a live market environment—without real money—for 6 to 12 months. This step exposes them to real-time dynamics like slippage, commissions, and data anomalies not fully captured in backtests. Many strategies falter here, revealing flaws that save traders from losses. Kevin cites a survey of his students, where 85-90% credit incubation with avoiding bad strategies or confirming good ones. This patience, though challenging, is a differentiator in a field where most rush to deploy untested algorithms.

Managing a Diversified Portfolio and Continuous Improvement

Once validated, strategies join Kevin’s portfolio library, where diversification is key. He balances risk across sectors using margin as a proxy for sector risk-exposure, ensuring no single market dominates. For instance, a loss in crude oil might be offset by gains in bonds or metals, smoothing the equity curve. However, trading futures—a zero-sum game—demands psychological resilience. Kevin acknowledges that drawdowns are inevitable, requiring traders to endure pain without abandoning their process—a subtle edge in itself.

Continuous improvement is equally vital. Markets evolve, and past successes don’t guarantee future results. Kevin constantly develops new strategies, adapting to shifts like the unprecedented cocoa rally that broke some of his older algorithms. This relentless refinement, rooted in his quality assurance background, keeps his portfolio competitive.

Conclusions

A critical aspect to Kevin's entire process is 'subbing in and out' on a monthly basis: that is, removing poor performing strategies and substituting in better performing ones from his library of over 200 strategies, where generally only 20 or so will be deployed at a time. These strategies will be spread across around 40-50 futures symbols, and he always attempts to keep an equal risk exposure to the seven distinct sectors. Certain rules (such as this sector diversification or forcing short equities models) are followed based on risk management principles, despite the back-test results. This is wise way of avoiding over-fitting and ensuring his risk of ruin is zero. In summary, the entirety of Kevin's process maximizes productivity and returns, for the right amount of risk (both market and operational risks), while keeping the strategies in tune with the current market conditions.

In the cutthroat world of algorithmic futures trading, a structured process is non-negotiable. Kevin Davey’s approach—defining objectives, rigorous validation via walk-forward and Monte Carlo methods, live incubation, and proactive portfolio management—offers advanced quantitative traders a framework to thrive. By blending engineering precision with market adaptability, his methodology underscores that success lies not just in the strategies themselves, but in the disciplined process behind them.

Trade well and prosper!

Contacts and more over on the website!

So is it any different to being a good engineer? Surgeon? Farmer? Isn't it sufficient to just commit to something long enough, keep getting up after knockdowns, train harder, study more, practice, and eventually, become "good enough" to be a master at your trade? I'm not trying to win a gold medal; I'm trying to generate sufficient success to make a living. "How can I out-perform my peers then" one might ask. I'm not trying to! I'm happy to match them. I just want to be in that percentile of traders who do really well, over the long term. In the process, I may out-perform a lot of the plain vanilla funds, but there's a reason for that: they have specific motivations, are driven by different (peer-and-market-following) mandates, restricted by trading enormous amounts of capital, use outdated tools, have to wade through piles of corporate red tape and regulatory burdens, etc., etc.

I mention this because when you talk to a guy who has spent decades on the craft, and carved out amazing results along the way, the over-riding theme is the refinement and enhancement of the process over time. Developing the right process, using the right tools, applying the right mindset, gosh, these are an edge right. These are the things to be working on. You don't have to be born with it, although it helps if you've got the right personality, for sure. That's another topic we'll get into with Brett Steenbarger when we talk to him on the show soon. So, I think the good news is that with a podcast like this, you get a free masterclass from the masters, and you should invest the time in making the most of it. If there's better questions I could ask, or people you'd like me to talk to, heck, just email me, I'll get on it.

What Is Walk-Forward Analysis?

Walk-forward analysis (WFA) is a systematic method to validate trading strategies by iteratively optimizing parameters on in-sample data and testing performance on subsequent out-of-sample data. Unlike traditional optimization, WFA simulates real-world trading by "rolling" the optimization window forward over time. This generates an entire back-test out of out-of-sample results, seeking to be scientific and systematic about developing strategies which will adapt to evolving market conditions while avoiding overfitting.

Key Principles for Robust Strategy Development

You must still validate: There are still traps, and art and science must still meet. A single walk-forward test may not be enough. Explore ways to use the WFA method. Apply the scientific method to use the tool to explore the data. It's going to take targeted effort to work out how to make WFA work for the time-frame and strategy-type you are developing.

Assessing the results: Profitability alone isn’t sufficient. Look for stable performance across all out-of-sample windows, be aware of regime shifts, trade counts, specific strategy strengths and weaknesses. Explore different time periods, different objective functions, and so on.

Avoid curve-fitting: WFA exposes over-optimized strategies. If parameters spike in isolated windows but fail elsewhere, the strategy is likely fragile.

Objective function design: Prioritize risk-adjusted metrics (e.g., profit/drawdown) over raw returns. Bob emphasizes tools that assess equity curve smoothness and trade distribution. Reject parameters that work only in narrow ranges. Seek "plateaus" where neighboring values perform similarly.

Regime awareness: Understand that strategies are tied to the data they’re built on. Test across bull, bear, and sideways markets to ensure adaptability.

Sample size sensitivity: High-frequency strategies naturally offer more data, but longer-term approaches (e.g., trend-following) require careful window sizing or bespoke methods to generate the needed sample size. Consider testing on other markets.

Risk management: The iterative process highlights variations in trade frequency, drawdowns, and profit consistency, allowing traders to refine their strategies and manage risk more effectively.

Final Takeaways

Bob’s framework prioritizes adaptability and empirical rigor. By combining WFA with curated tools (e.g., Ranger) and disciplined evaluation, traders can:

• Identify strategies that perform consistently across regimes.

• Minimize overfitting risks inherent in traditional optimization.

• Build diversified portfolios of uncorrelated strategies for smoother equity curves.

• Have a built-in process for on-going monitoring and updates of strategies.

For advanced traders, the key lies in balancing automation with strategic intuition - leveraging WFA to validate ideas while respecting market complexity.

As always, check the website for more.

Trade well and prosper!