A self-used quantitative trading framework
Comprehensive quantitative trading framework with deep learning/strategy development/backtesting/live trading
Tech Stack
Quantitative Trading Framework
🎯 Author's Preface
I developed an interest in quantitative trading around the end of 2023 and built the core code of this framework, deploying it on AWS for live trading. However, the returns over several months were not ideal, and risk control was also suboptimal. Eventually, after half a year, I paused further development.
Looking back now (in 2025), this framework is still quite comprehensive in terms of functionality, but I simply don't have the bandwidth to continue updating it. Given the rapid advancements in AI, I no longer plan to manually maintain this project as I once did. Instead, I intend to develop a new trading system from scratch using Cursor and seek to join a part-time quantitative trading team to learn and collaborate.
That said, this framework still documents some of my self-taught achievements in quantitative trading, so I've decided to open-source it here for discussion and exchange.
💡 Contact Me: If your quant team is hiring or if you'd like to explore quantitative trading methods together, feel free to reach out!
The above content was handwritten by me. The following content is AI-generated.
📊 Project Overview
A comprehensive quantitative trading system that integrates machine learning models, real-time data processing, and automated trading execution. The system supports multiple broker APIs and provides end-to-end solutions for strategy development, backtesting, and deployment.
✨ Key Features
| Feature | Description | Benefits |
|---|---|---|
| 📈 Strategy Development | Modular framework for developing and testing trading strategies | Flexible & Extensible |
| 🧠 Machine Learning Integration | LSTM and other ML models for price prediction | Intelligent Forecasting |
| 🔗 Multi-Broker Support | Integrated APIs for Alpaca, Tradier, and other brokers | Multi-platform Compatible |
| ⚡ Real-time Data Processing | Automated data acquisition and feature engineering | Real-time Response |
| 🔄 Backtesting Engine | Comprehensive backtesting with performance analytics | Historical Validation |
| ☁️ Cloud Deployment | AWS-ready deployment with scheduled task management | Stable Operation |
| 🛡️ Risk Management | Built-in position management and risk controls | Safety Assured |
🛠️ Technology Stack
Core Technologies
Languages: Python
ML Frameworks: TensorFlow/Keras, scikit-learn
Data Sources: Yahoo Finance, broker APIs
Deployment: AWS EC2
Key Dependencies
# Data Processing
pandas
numpy
yfinance
# Machine Learning
tensorflow
keras
scikit-learn
# Trading & Backtesting
backtesting
alpaca-trade-api
📁 Project Structure
algorithm_trading_framework/
├── 📂 main/ # Production trading strategies
├── 📂 strategy_develop/ # Strategy development and research
├── 📂 data_develop/ # Data acquisition and feature engineering
├── 📂 wheels/ # Common APIs and utilities
└── 📂 config/ # Configuration and credentials management