Dimensionless-Quant-Finance-App

A full-stack, multi-asset algorithmic trading research platform with predictive modeling, backtesting, and portfolio optimization.

📈 Quantitative Trading Platform

🧠 Overview

A full-stack, multi-asset algorithmic trading research platform with predictive modeling, backtesting, and portfolio optimization.

Current Status: ✅ Backend-Frontend Integration Complete | ⏳ Live Trading is reserved

Live Product: (https://algo.dimensionlessdevelopments.com)

🎯 Key Achievements

✅ Production Deployment - Live
✅ Multi-Asset Support - Stocks, Crypto, Forex, Indices
✅ Advanced ML Models - ARIMA + GARCH predictive analytics
✅ Regime-Adaptive Strategy - Dynamic strategy switching based on market conditions
✅ Comprehensive Testing - 25+ integration tests, 100% core functionality coverage
✅ Type-Safe Architecture - Full TypeScript + Pydantic validation

🚀 Quick Start

Prerequisites

• Python 3.14+ with venv activated
• Node.js 16+ and npm
• Internet connection (for market data)

1. Start Backend

# Activate virtual environment
.\venv\Scripts\Activate.ps1

# Install dependencies (first time only)
pip install -r requirements.txt

# Start backend server
python start_backend.py

Backend runs on: http://localhost:8000

2. Start Frontend

# In a new terminal
cd front

# Install dependencies (first time only)
npm install

# Start development server
npm run dev

Frontend runs on: http://localhost:5173

3. Access Dashboard

Open browser to: http://localhost:5173

---

🧱 Architecture

Data Flow:

Market Data (yfinance) 
    ↓
Feature Engineering (Bollinger, %B, Volatility)
    ↓
Predictive Models (ARIMA/GARCH)
    ↓
Signal Generation (Hybrid Regime Strategy)
    ↓
Backtesting (Positions, Returns, Metrics)
    ↓
API Layer (FastAPI REST endpoints)
    ↓
Frontend Dashboard 

---

⚙️ Core Functionality

✅ Fully Implemented

1. Data Ingestion

• Historical data via yfinance
• Multi-asset support (SPY, QQQ, BTC-USD, forex)
• OHLCV data processing

2. Feature Engineering

• Bollinger Bands (MA ± 2σ)
• Percent B indicator (%B)
• Rolling volatility
• Log returns

3. Predictive Modeling

• ARIMA → Return forecasts
• GARCH → Volatility forecasts
• Risk-adjusted score: predicted_return / predicted_volatility

4. Hybrid Signal Engine

• Low Volatility Regime: Mean reversion using Bollinger Bands
• High Volatility Regime: ARIMA/GARCH predictive signals
• Adaptive strategy based on market conditions

5. Backtesting Engine

• Realistic position sizing
• Avoids look-ahead bias
• Strategy vs. market comparison
• Cumulative return tracking

6. Performance Analytics

• Metrics: Total Return, CAGR, Sharpe Ratio, Max Drawdown, Win Rate, Profit Factor
• Visualizations: Equity curve, drawdown chart
• Regime Analysis: Volatility classification and history

7. Optimization Suite

• Threshold optimization
• Walk-forward analysis (train → test → roll)
• Multi-parameter grid search

8. Portfolio Engine

• Multi-asset combination
• Equal-weight allocation
• Time-series alignment
• Missing data handling

9. API Layer (Backend)

• FastAPI with auto-generated docs
• 3 REST endpoints:
  • GET /api/dashboard?symbol={symbol} - Full dashboard data
  • GET /api/signals?symbol={symbol} - Recent signals
  • POST /api/backtest - Custom date range backtest
  • POST /api/optimize - Multi-parameter threshold optimization
  • POST /api/portfolio - Multi-asset portfolio analysis
  • POST /api/backtest-risk - Risk management with stop-loss/take-profit
• Type-safe Pydantic models with validation
• Production CORS with environment-based configuration
• Health monitoring endpoint for uptime checks

10. Frontend Dashboard

• React + TypeScript with Vite
• Components:
  • Bollinger Band chart
  • Metrics panel (Sharpe, returns, drawdown)
  • Signal history
  • Equity curve
  • Volatility regime indicator
• Real-time data from backend API
• Error handling and retry logic

---

📡 API Endpoints

GET /api/dashboard?symbol={symbol}

Returns comprehensive dashboard data:

{
  "symbol": "SPY",
  "lastUpdate": "2024-04-06T10:30:00",
  "bollinger": [...],
  "signals": [...],
  "metrics": {
    "totalReturn": 23.47,
    "sharpeRatio": 1.84,
    "maxDrawdown": -8.23,
    ...
  },
  "equity": [...],
  "regime": {...}
}

GET /api/signals?symbol={symbol}

Returns recent trading signals.

POST /api/backtest

Run backtest with custom date range:

{
  "symbol": "SPY",
  "start": "2020-01-01",
  "end": "2024-01-01"
}

API Docs: http://localhost:8000/docs

---

📂 Project Structure

quant/
├── backend/                 # Python backend
│   ├── app/
│   │   ├── api/            # FastAPI routes
│   │   ├── backtest/       # Backtesting engine
│   │   ├── data/           # Data loading
│   │   ├── models/         # ARIMA/GARCH/Indicators
│   │   ├── optimization/   # Parameter optimization
│   │   ├── performance/    # Analytics
│   │   ├── portfolio/      # Multi-asset
│   │   └── strategy/       # Signal generation
│   ├── test_.py           # Integration tests
│   └── ...
├── front/                   # React frontend
│   ├── src/
│   │   ├── components/     # UI components
│   │   ├── pages/          # Dashboard page
│   │   └── lib/            # API client
│   └── ...
├── scripts/                 # Development utilities
├── start_backend.py        # Backend startup script
├── requirements.txt        # Python dependencies
├── INTEGRATION_GUIDE.md    # Setup guide
└── README.md               # This file

---

🧪 Testing

Run Backend Tests

python backend/test_portfolio.py
python backend/test_optimization.py
python backend/test_walkforward.py

Test API Endpoints

# Health check
curl http://localhost:8000/health

# Get dashboard
curl "http://localhost:8000/api/dashboard?symbol=SPY"

Test Frontend

1. Start both backend and frontend
2. Open http://localhost:5173
3. Verify data loads (not mock data)
4. Check browser console for errors

---

📚 Documentation

• INTEGRATION_GUIDE.md - Complete setup guide, troubleshooting
• INTEGRATION_COMPLETE.md - What was built, what's next
• scripts/README.md - Utility scripts documentation
• API Docs - Auto-generated at http://localhost:8000/docs

---

🔄 Workflow

1. Data Pipeline

   • Fetch historical data
   • Calculate features
   • Run models

2. Signal Generation

   • Analyze volatility regime
   • Generate hybrid signals
   • Apply entry/exit rules

3. Backtesting

   • Simulate positions
   • Calculate returns
   • Compute metrics

4. Visualization

   • Display in dashboard
   • Interactive charts
   • Performance analysis

---

🎯 Key Design Principles

• Modular Architecture - Separable, testable components
• Type Safety - Pydantic (backend) + TypeScript (frontend)
• Separation of Concerns - Data/Models/Strategy/UI layers
• Regime Awareness - Adaptive strategy based on market conditions
• Research-First - Emphasis on backtesting before live trading

---

📈 Performance Notes

• First request takes 5-10 seconds (ARIMA/GARCH fitting)
• Default analysis: 2 years of daily data
• Supports: Stocks (SPY), Crypto (BTC-USD), Forex (EURUSD=X)
• Consider caching for production use

---

🛠️ Tech Stack

Backend:

• FastAPI (REST API)
• Pandas/NumPy (Data processing)
• yfinance (Market data)
• statsmodels (ARIMA)
• arch (GARCH)
• Pydantic (Data validation)

---

🐛 Troubleshooting

Backend Won't Start

• Ensure venv is activated
• Install dependencies: pip install -r requirements.txt
• Check port 8000 is available

Frontend Can't Connect

• Verify backend is running: curl http://localhost:8000/health
• Check CORS settings in backend/app/main.py
• Clear browser cache

Slow Performance

• First request is slow (model fitting)
• Consider implementing caching
• Reduce date range for testing

See INTEGRATION_GUIDE.md for more troubleshooting.

---

📝 License

MIT License - See LICENSE file for details

---

🤝 Contributing

1. Fork the repository
2. Create feature branch (git checkout -b feature/amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin feature/amazing-feature)
5. Open Pull Request

---

📞 Support

• Check documentation in /docs folder
• Review API docs at http://localhost:8000/docs
• See troubleshooting in INTEGRATION_GUIDE.md

---

✨ Status Summary

What Works: ✅ Full-stack integration
✅ Multi-asset backtesting
✅ ARIMA/GARCH modeling
✅ Hybrid regime strategy
✅ Performance analytics
✅ Interactive dashboard
✅ REST API

What's Next: ⏳ Live trading infrastructure

---

Built with ❤️ for quantitative trading research

Dimensionless-quant

---

Contact

Made by Dimensionless Developments Head to our website https://www.dimensionlessdevelopments.com ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ Email: contact@dimensionlessdevelopments.com