A research-grade quantitative trading framework for backtesting and strategy development.

Download → Extract → Run in 3 commands:

# 1. Download ZIP from GitHub and extract
# 2. Open terminal in extracted folder
# 3. Run the portable backtest:

python .\一键回测_portable.py --mode fast --years 3

That's it! The script will:

• ✅ Automatically create virtual environment (.venv/)
• ✅ Install minimal dependencies (2-3 minutes first time)
• ✅ Download market data (Yahoo Finance with Stooq fallback)
• ✅ Run backtest using simple SMA strategy
• ✅ Generate JSON report in backtest_reports/

Advanced features (optional):

# Enable AI-powered strategies (requires OpenAI API key)
python .\一键回测_portable.py --mode fast --ai

# Quick test with 1 year, 2 stocks
python .\一键回测_portable.py --mode turbo --years 1 --symbols AAPL MSFT

# Custom symbols
python .\一键回测_portable.py --symbols AAPL GOOGL NVDA TSLA

⚠️ Path Length Note: If you see warnings about long paths or parentheses, move the folder to a shorter location (e.g., C:\Stock_Deepseeker\)

This is an active research project focused on building a solid quantitative trading infrastructure. It is NOT production-ready and should NOT be used for live trading without substantial additional work.

• ✅ Event-driven backtest engine with no-lookahead bias enforcement
• ✅ 62+ quantitative factors across 6 categories
• ✅ Basic risk management modules (VaR, position limits, stop-loss)
• ✅ Multiple strategy templates
• ✅ Data providers (Yahoo Finance, Alpha Vantage)
• ✅ Performance analytics and reporting

• ❌ Production trading system
• ❌ "Institutional-grade" or "Enterprise-level"
• ❌ Fully tested and validated
• ❌ Ready for live trading
• ❌ Complete or feature-complete

Stock_Deepseeker/
├── src/                    # Core library
│   ├── backtest/          # Event-driven backtest engine
│   ├── data/              # Data providers and loaders
│   ├── factors/           # Quantitative factor library (62+ factors)
│   ├── strategies/        # Strategy templates
│   ├── risk/              # Risk management modules
│   ├── execution/         # Order execution simulation
│   ├── monitoring/        # System monitoring
│   └── analytics/         # Performance analytics
├── examples/              # Usage examples (educational)
├── tests/                 # Test suite (partial coverage)
└── docs/                  # Documentation

Event-driven architecture designed to prevent lookahead bias:

• engine_v2.py: Main backtest engine with strict time-ordering
• events.py: Event system (Market, Signal, Order, Fill)
• portfolio_v2.py: Portfolio tracking and management
• execution.py: Order execution simulation

62+ quantitative factors across:

• Momentum (13 factors)
• Value (14 factors)
• Quality (13 factors)
• Volatility (12 factors)
• Growth (10 factors)
• Liquidity (11 factors)

• Momentum
• Mean Reversion
• Pairs Trading
• Value Investing
• Multi-Factor
• Volatility Arbitrage
• Sector Rotation
• Breakout
• Trend Following
• Market Neutral

# Clone repository
git clone https://github.com/YOUR_USERNAME/Stock_Deepseeker.git
cd Stock_Deepseeker

# Install dependencies
pip install -e .

# Optional: Install development dependencies
pip install -e ".[dev]"

最简单的方式 - 使用完整的回测脚本：

# 使用模拟数据运行回测（用于演示）
python run_backtest.py --mock

# 使用真实数据（需要网络连接）
python run_backtest.py --symbols AAPL

# 自定义参数
python run_backtest.py --symbols AAPL MSFT --start 2023-01-01 --capital 50000 --mock

# 查看所有选项
python run_backtest.py --help

特性：

• ✅ 完整的端到端回测示例
• ✅ 使用真实的 Yahoo Finance 数据或模拟数据
• ✅ 双均线交叉策略（可定制参数）
• ✅ 详细的回测结果报告
• ✅ 100% 可运行，无需额外配置

查看 examples/ 目录了解更多用法：

python examples/basic_backtest.py

注意: 示例代码是教学性骨架，run_backtest.py 是完整实现。

# Run all tests
pytest tests/

# Run with coverage
pytest tests/ --cov=src --cov-report=html

Current test status:

• 191 tests collected (imports work)
• Partial test coverage
• Some tests are templates/incomplete

• Clean up architecture
• Remove duplicate code
• Complete test coverage for core modules
• Validate no-lookahead enforcement
• Document actual capabilities

• Robust data ingestion
• Corporate actions handling
• Survivorship bias elimination
• Data quality checks

• Connect risk modules to backtest
• Real-time risk monitoring
• Position sizing
• Portfolio constraints

• Standardized strategy interface
• Factor integration
• Signal generation
• Portfolio optimization

• Comprehensive testing
• Performance optimization
• Broker integrations
• Live trading capabilities

1. Test Coverage: Many tests are incomplete or template-based
2. Integration: Components not fully integrated (data → strategy → backtest → risk)
3. Documentation: Some docs describe planned, not actual features
4. Performance: Not optimized for large-scale backtesting

This is a research project. Contributions welcome, but please:

1. Write tests for new features
2. Update documentation to reflect actual capabilities
3. Follow existing code style
4. Be honest about limitations

This software is for educational and research purposes only.

• NOT financial advice
• NOT production-ready
• NOT guaranteed to be correct
• NO warranty of any kind

Use at your own risk. Past performance does not predict future results.

[Your License Here]

[Your Contact Info]

Built with honesty in mind 🎯