Cross-sectional Transformer and FFN for stock return prediction and alpha generation. Implements GKX (2020) NN5 replication and MSRR loss (Kelly et al. 2025) for direct portfolio Sharpe optimization. Avg SDF Sharpe 2.05, significant alpha (t=5.34) unexplained by FF5+Momentum.

End-to-end algorithmic trading system using PyTorch LSTM. Features a custom Cross-Sectional Alpha ranking engine, dynamic portfolio compounding, and event-driven backtesting (+483% return vs SPY).

A Python trading bot that combines momentum, mean reversion, and volatility signals to run a long-short strategy. Includes a custom walk-forward optimizer to automatically tune the model as market conditions change.

An open-source framework for autonomous digital entities, focused on decentralized threat & alpha intelligence.

Quantitative Research framework for cross-sectional equity factor ranking. Evaluates Value (EY) and Quality (ROC) factors with point-in-time integrity and sector-neutrality.

A quantitative framework modeling recursive interactions between technology, capital, and delayed information absorption.

A comprehensive, production-grade implementation of quantitative trading strategies across 18 asset classes. Features modular Python architecture, institutional risk management, and deep-dive research papers for every strategy.

Strat-ML: S&P 500 Alpha Generation Framework:- This repository contains a complete quantitative pipeline designed to outperform the S&P 500 Index using Machine Learning. The project focuses on out-of-sample signal generation using constituent-level OHLCV data, rigorous Blocking Time Series Cross-Validation, and a Long/Short Stock Picking strategy.