Skip to content

Repository files navigation

Aurora: Genetic Algorithm HFT Strategy Evolver 🧬⚡

Developer

alwaysprince05

Project Overview 🚀

Aurora is a highly sophisticated, AI-driven quantitative terminal designed to automatically discover, optimize, and evolve trading strategies using Genetic Algorithms. By mirroring the principles of biological evolution—selection, crossover, and mutation—this engine dynamically generates optimized trading parameters (such as moving averages and crossover thresholds) tailored to survive and profit in varying market conditions.

The system features a Professional HFT Trading Dashboard, providing real-time, interactive insights into the evolution process. Experience automated algorithmic discovery at its finest!

Aurora HFT Dashboard

Core Features ✨

  • Aurora HFT Dashboard: A sleek, ultra-dark Binance/Bloomberg inspired terminal built with vanilla CSS, glassmorphism UI, and interactive Chart.js graphs.
  • Dynamic Market Regimes: Simulate your algorithm's survivability against dynamically generated asset prices. Choose between Random Walk, Bull Market, Bear Market, or High Volatility regimes.
  • Fully Stochastic Engine: Every evolution run is entirely unique and non-deterministic.
  • Robust Fitness Evaluation: Multi-metric performance tracking optimizing for Total Return, Sharpe Ratio, Max Drawdown, Win Rate, and Total Trades.
  • Advanced Technical Charts: Visualize your simulated Equity Curve overlaid directly on the underlying Asset Price, complete with vertical index crosshairs for analyzing parameter convergence.

Quick Start 💻

  1. Clone the Repository
    git clone https://github.com/alwaysprince05/Genetic-Algorithm-Strategy-Evolver.git
    cd Genetic-Algorithm-Strategy-Evolver
  2. Setup Virtual Environment & Install Dependencies
    python3 -m venv venv
    source venv/bin/activate
    pip install Flask numpy pandas matplotlib
  3. Launch the HFT Terminal
    python app.py
    Then open http://localhost:5000 in your web browser. The terminal will automatically initialize the first evolutionary sequence on load!

Relevant Concepts 📚

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages