Evolutionary Strategy Research

A research framework for evolving trading strategies using genetic programming and evolutionary algorithms. This project provides tools for automatically discovering strategy building blocks, running reproducible experiments, and evaluating candidate strategies through backtesting.

🎯 Goals

• Automatic Strategy Discovery: Discover strategy building blocks automatically using genetic programming
• Reproducible Experiments: Versioned data and environment capture for consistent results
• Latency-Aware Backtesting: Backtesting primitives that account for execution latency
• Clear Promotion Path: Structured workflow from evolution → out-of-sample testing → stress testing → candidate pool

✨ Features

• Genetic programming engine for strategy evolution
• Synthetic data generation for testing
• Docker containerization for easy deployment
• Distributed computing support via Ray
• Modular architecture for easy extension