Skip to content
View ryousuf569's full-sized avatar

Block or report ryousuf569

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ryousuf569/README.md

Yousuf Rashid

📍 Waterloo, ON
🎓 Honours Mathematics (Co-op) @ University of Waterloo

LinkedIn · Portfolio


About Me

I'm a Mathematics student at the University of Waterloo with a strong interest in quantitative research, data science, and machine learning applied to real-world decision making.

I enjoy working at the intersection of:

  • Probability & statistics
  • Time-series analysis
  • Simulation & empirical research
  • Interpretable machine learning

I focus on building systems that answer real questions, not just models that look good on paper.


Current Work

Student Machine Learning Researcher — Wat.AI
Jan 2026 – Present

  • Conducting early-stage research on LLM-free sentiment analysis of financial news
  • Integrating FinBERT-derived sentiment signals with market metrics (returns, volatility)
  • Designing interpretable research pipelines using NumPy, pandas, SciPy
  • Evaluating sentiment-based factors for empirical robustness and signal quality

Projects

Stochastic Simulation for Index Futures

Python, NumPy, pandas

  • Built a domain-specific query language to express stochastic simulation intent over financial time series
  • Ran 10,000+ Monte Carlo simulations per query using bootstrap sampling
  • Detected p-hacked strategies with 68% accuracy, preventing ~$2,000 in paper-trading losses
  • Ranked technical indicators using correlation and (R^2) for signal selection

Music Listener Engagement Analysis

Python, scikit-learn, SQLite

  • Modeled listener engagement using Hidden Markov Models
  • Identified skip-prone segments accounting for 21.3% of track duration
  • Built probabilistic state inference using Multinomial Logistic Regression
  • Designed a normalized relational database for per-second engagement analytics

NBA Fantasy Performance Predictor

Python, XGBoost, FastAPI, React

  • Processed 5,000+ rows of NBA performance data
  • Built ML pipelines with XGBoost (performance prediction) and KNN (player similarity)
  • Improved lineup decisions by 30% over rolling windows
  • Deployed a FastAPI backend with a React/TypeScript frontend

Technical Skills

Languages
Python · R · SQL · C/C++ · MATLAB · VBA

Data & ML
pandas · NumPy · scikit-learn · SciPy · XGBoost · TensorFlow · matplotlib

Frameworks & Databases
FastAPI · React · Next.js · PostgreSQL · SQLite · SQLAlchemy

Tools
Git · GitHub · Linux · VS Code · Tableau · Power BI · Excel


Technical & Academic Activities

  • Robotics Software Lead (Skills Canada)
    Led C++ development for an autonomous robot achieving 85% run success
  • Bloomberg Market Concepts
    Analyzed macroeconomic indicators, bond valuation, and central bank policy
  • Deep Learning with TensorFlow
    Studied CNNs and RNNs to inform model selection for production systems

Interests

  • Quantitative research & trading systems
  • Time-series modeling
  • Simulation & Monte Carlo methods
  • Interpretable machine learning
  • Turning theory into working tools

Open to: Quant Research, Data Science, ML, and FinTech co-op opportunities

Pinned Loading

  1. SonarQL SonarQL Public

    A query-driven stochastic simulation engine that performs feature selection and statistical diagnostics on time-series data.

    Python

  2. fantasy-add-drop-recommender fantasy-add-drop-recommender Public

    Discontinued, backend cost making my wallet empty. Stats.nba.com now blocks a lot of pull requests from external addresses, so the site's functionality does not go all too well anymore.

    TypeScript

  3. midi-me midi-me Public

    A statistical model to identify listener engagement zones in songs

    Python

  4. audio-qa-automation audio-qa-automation Public

    A quick engine for a bigger project I'm working on.

    C++