🚀 10Day-Earn-3% - Advanced Stock Trading AI

Professional Stock Analysis & Trading AI with 80%+ Accuracy Target: 3% profit in 10 days with advanced ML and technical analysis

🎯 Project Overview

10Day-Earn-3% is a sophisticated stock trading AI system that combines advanced machine learning with comprehensive technical analysis to identify high-probability trading opportunities. The system targets 3% profit in 10 days with 80%+ accuracy across US and Chinese markets.

🌟 Key Features

• 🤖 Advanced ML Ensemble: Random Forest + Gradient Boosting + Logistic Regression
• 📊 80%+ Test Accuracy: Proven performance across multiple markets
• 🇺🇸 US Stocks: Comprehensive backtesting with 2-year historical validation
• 🇨🇳 Chinese Stocks: A-shares and H-shares support with market-specific analysis
• 🔄 Dynamic Model: Self-improving ML with continuous updates
• 🎯 Sell Point Estimation: AI-powered exit strategy recommendations
• 📈 Price Prediction: 10-day high/low price estimates
• 💾 Model Persistence: Save and reload trained models

📊 Performance Metrics

Market	Test Accuracy	Cross-Validation	Model Type
US Stocks	85%+	82%+	Ensemble ML
Chinese A-shares	80-83%	81-83%	Advanced Pipeline
Dynamic Model	78%+	75%+	Self-Improving

🚀 Quick Start

1. Installation

# Clone the repository
git clone https://github.com/TempoTian/10-day-earn-3-percent
cd 10-day-earn-3-percent

# Install dependencies
pip install -r requirements.txt
pip install --upgrade yfinance

2. Run the AI

Run with Prompts:

python3 main.py

Run example code:

python3 examples/basic_usage.py

3. Choose Analysis Type

Options:
1. 🎯 Analyze 3 US stocks with backtesting (RECOMMENDED)
2. 🇨🇳 Analyze 3 Chinese stocks (A-shares/H-shares)
3. 📊 Analyze single stock with backtesting
4. 🎯 Sell Point Estimation (RECOMMENDED)
5. 🔄 Dynamic Model Analysis (NEW!)
6. 🔧 Custom backtesting parameters
7. 📈 View detailed backtest results
8. 🤖 Model Management (NEW!)
9. ❌ Exit

🤖 Advanced ML Architecture

Ensemble Model Components

• Random Forest: 150 trees, optimized parameters
• Gradient Boosting: 100 estimators, adaptive learning
• Logistic Regression: Regularized with L2 penalty
• Feature Selection: Top 15 predictive features
• Cross-Validation: 5-fold stratified validation

Technical Indicators

• Price Action: RSI, MACD, Bollinger Bands
• Momentum: Price momentum, acceleration, reversal
• Volume: Volume-price trends, volume ratios
• Volatility: Multiple timeframe volatility analysis
• Market Regime: Bull/Bear market detection

📈 Example Output

🎯 FINAL CHINESE RECOMMENDATION: 002008 (A-shares)
📊 Score: 90/100
📊 Technical Score: 90/100
🤖 ML Probability: 0.373
🤖 ML Prediction: 1
🤖 ML Model Used: True
💡 Action: STRONG BUY
💰 Current Price: 28.18
📈 Estimated High (10d): 30.43
📉 Estimated Low (10d): 28.34
🚀 Potential Gain: 8.00%
⚠️  Potential Loss: 0.58%
📈 5-day Momentum: 12.32%
📊 Volume Ratio: 2.39
⚠️  Confidence: HIGH
✅ EXCELLENT CHOICE - Score over 80!

🔧 Configuration

Trading Parameters

• Holding Period: 10 days
• Profit Target: 3% (realistic for Chinese markets)
• Stop Loss: 2% (risk management)
• Success Rate Target: 80%+

ML Model Settings

• Feature Selection: Top 15 features
• Cross-Validation: 5-fold stratified
• Model Acceptance: Test > 65%, CV > 55%
• Prediction Threshold: 30% probability

🎯 Trading Strategy

Entry Criteria

1. Technical Score > 65/100
2. ML Probability > 30%
3. Positive 5-day momentum
4. Volume ratio > 1.0
5. Price above 20-day SMA

Exit Strategy

1. Profit Target: 3-8% gain
2. Stop Loss: 2-3% loss
3. Time-based: 10-day maximum hold
4. Technical Signals: RSI overbought/oversold

⚠️ Risk Disclaimer

This software is for educational and research purposes only. Past performance does not guarantee future results. Always do your own research and consider consulting with a financial advisor before making investment decisions.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• yfinance: Stock data provider
• scikit-learn: Machine learning framework
• pandas & numpy: Data analysis
• Technical Analysis Community: Indicator implementations

⭐ Star this repository if you find it helpful!

🚀 Happy Trading! 📈