The official PyTorch code implementation of "Human Trajectory Prediction via Counterfactual Analysis" in ICCV 2021.

BITES: Balanced Individual Treatment Effect for Survival data

An interpretable early-warning engine that detects academic instability before grades collapse. Instead of predicting performance, it models pressure accumulation, buffer strength, and transition risk using attendance, engagement, and study load to explain fragility and identify high-leverage interventions.

An interpretable battery health engine that detects hidden points of no return instead of just predicting health %. It models stress, buffer, and degradation intensity, discovers Stable/Drifting/Irreversible regimes via GMM, and learns simple Decision Tree thresholds, with a Streamlit app for diagnostics and what-if scenarios.

An explanation-first HR analytics system that reconstructs why employee exit becomes rational. Instead of predicting attrition, it generates human-readable exit narratives by decomposing pressure and retention forces, adding peer context and counterfactual interventions to reveal how stability erodes over time.

A systems-level analysis engine that models sleep as a recovery debt process rather than a nightly outcome. Using physiological traits and ecological pressure signals, it estimates predicted sleep need, quantifies sleep debt, and visualizes how stress accumulates silently before visible fatigue or failure occurs.

Colibri — execution + intelligence + legitimacy (MCP server + agent orchestration platform)

State space model + data pipeline to generate counterfactual time series trajectories on multiple clinical signals, used to evaluate the utility of counterfactual features in sepsis prediction

Estimation of the Population Impact Fraction and Potential Impact Fraction

This repository contains data and code for counterfactual time series analysis of air pollutant concentrations in the United States.

Code to demo counterfactual evaluation on synthetic demo

Fan Chart for Economic Uncertainty

Stock-Flow Consistent Agent-Based Macroeconomic Engine

Quantification of protected areas effectiveness for conservation of biomass carbon stocks

🔋 Detect and analyze irreversible degradation thresholds in batteries, enhancing health analytics and extending battery life through informed decision-making.

This repository contains code which accompanies the paper: Assessing Model Behaviour on Extreme Counterfactuals (https://www.researchgate.net/publication/360912277_Assessing_Model_Behaviour_on_Extreme_Counterfactuals)

Uplift-based P&L modeling for subscription impact using RFM-segmented daily counterfactual comparison

CausalAnalysisDoWhyCounterFactualNetworks_FreemiumGameplayChurn_EngineeredSyntheticData

Read-only mirror of a descriptive, non-operational paper on interpretive friction and incentive dynamics in AI-only encounters.