Premchan369
/

alphaforge-quant-system

@@ -1,149 +1,154 @@
-# AlphaForge - Multi-Asset Quantitative Trading System
-A comprehensive quantitative trading system that combines price-based alpha signals, financial sentiment analysis, volatility forecasting, portfolio optimization, and ML-based options pricing.
-## Features
-### 1. Multi-Asset Alpha Model
-- **LSTM** neural network for sequential pattern recognition
-- **Transformer** architecture for attention-based forecasting
-- **XGBoost** ensemble for robust feature-based predictions
-- **Ensemble** combining all three with IC-weighted blending
-- **IC Tracking**: Information Coefficient monitoring over time
-- **Feature Drift Detection**: XGBoost importance divergence tracking
-### 2. News + Sentiment Alpha (FinBERT)
-- Uses `ProsusAI/finbert` for financial sentiment analysis
-- Converts news/social media into numerical alpha signals
-- Confidence-weighted aggregation per asset per day
-- Synthetic news generation for testing
-### 3. Volatility Forecasting Engine
-- **GARCH(1,1)** with Student-t errors for baseline
-- **LSTM** with skewed Student's t distributional output
-- **EWMA covariance** matrix construction
-- Positive definite enforcement
-### 4. Portfolio Optimizer
-- Mean-variance optimization with transaction costs
-- Max Sharpe ratio optimization
-- Minimum volatility with return constraints
-- **Robust optimization** with uncertainty sets
-- **Black-Litterman** model for incorporating views
-- Efficient frontier computation
-### 5. Options Pricing with ML
-- 4-layer neural network (256-128-64-32)
-- Black-Scholes baseline for comparison
-- Implied volatility prediction
-- **Mispricing detection** for arbitrage signals
-- Synthetic data generation for training
-### 6. Backtest Engine
-- Transaction cost and slippage simulation
-- Comprehensive metrics:
-  - Sharpe, Sortino, Calmar ratios
-  - Max drawdown, win rate
-  - Alpha, Beta, Information Ratio
-  - Turnover and cost analysis
-- Regime detection (bull/bear/high-vol)
-- Rolling performance metrics
-## Installation
-```bash
-git clone https://huggingface.co/Premchan369/alphaforge-quant-system
-cd alphaforge-quant-system
-pip install -r requirements.txt
-```
-## Usage
-### Train Alpha Model
-```bash
-python main.py --mode train --tickers SPY QQQ AAPL MSFT --epochs 50
-```
-### Run Full Backtest
-```bash
-python main.py --mode backtest --start 2020-01-01 --end 2024-01-01
-```
-### Train Options Model
-```bash
-python main.py --mode options
 ```
-## Pipeline Architecture
-```
-Market Data (OHLCV)
-    |
-    +---> Technical Indicators (RSI, MACD, Bollinger, etc.)
-    +---> Cross-Asset Features (beta, correlation, spreads)
-    |
-    v
-Alpha Model (LSTM + Transformer + XGBoost Ensemble)
-    |---> Predicted Returns (mu)
-    |---> IC Tracking
-    |
-News Data
-    |
-    v
-Sentiment Model (FinBERT)
-    |---> Sentiment Alpha (S_t)
-    |
-    v
-Combined Alpha = w1 * Price Alpha + w2 * Sentiment Alpha
-Market Data
-    |
-    v
-Volatility Engine (GARCH + LSTM)
-    |---> Covariance Matrix (Sigma)
-    |
-    v
-Portfolio Optimizer (Mean-Variance / Max Sharpe / Robust)
-    |---> Optimal Weights (w)
-    |
-    v
-Backtest Engine
-    |---> PnL, Sharpe, Drawdown, etc.
 ```
-## Key Metrics
-| Metric | Description |
-|--------|-------------|
-| **IC** | Information Coefficient (rank correlation between predicted and actual returns) |
-| **Sharpe** | Risk-adjusted return (excess return / volatility) |
-| **Sortino** | Downside risk-adjusted return |
-| **Max DD** | Maximum peak-to-trough decline |
-| **Calmar** | Annualized return / max drawdown |
-| **Alpha** | Excess return vs benchmark |
-| **Beta** | Market sensitivity |
-## File Structure
-| File | Description |
-|------|-------------|
-| `main.py` | Entry point and orchestration |
-| `market_data.py` | Data fetching and feature engineering |
-| `alpha_model.py` | LSTM/Transformer/XGBoost ensemble |
-| `sentiment_model.py` | FinBERT sentiment analysis |
-| `volatility_model.py` | GARCH + LSTM volatility forecasting |
-| `portfolio_optimizer.py` | Mean-variance and robust optimization |
-| `options_pricer.py` | ML options pricing and mispricing detection |
-| `backtest_engine.py` | Backtesting with comprehensive metrics |
-## Research Backing
-- **Alpha Models**: xLSTM-TS with wavelet denoising (Lopez Gil et al., 2024)
-- **Sentiment**: FinBERT (Araci, 2019) with ChatGPT benchmarking (Fatouros et al., 2023)
-- **Volatility**: LSTM with skewed Student's t (Michankow, 2025)
-- **Portfolio**: Multi-task learning for joint optimization (Ong & Herremans, 2023)
-- **Options**: 5-layer FNN outperforming Black-Scholes (Berger et al., 2023)
-## License
 MIT

+# 🏦 AlphaForge - Autonomous Quant Fund OS
+A **production-grade** quantitative trading system with 22 integrated modules — multi-source alpha generation, risk management, portfolio optimization, and derivatives pricing.
+## 🎯 Why This Is Different
+| Feature | Typical Student Project | AlphaForge |
+|---------|------------------------|------------|
+| Alpha Sources | Only price data | Price + Sentiment + Factors |
+| Model Architecture | Single model | Ensemble + Meta-Model |
+| Risk | Ignored | VaR, CVaR, Tail Risk, Drawdown Control |
+| Regime | Assumed constant | HMM Regime Switching |
+| Uncertainty | Point estimates | Bayesian Probabilistic |
+| Options | None | ML Pricing + Mispricing |
+| Hedging | None | Delta-Neutral Dynamic |
+| Explainability | None | SHAP + Feature Importance |
+| Anomaly Detection | None | Isolation Forest + Autoencoder |
+| Stress Testing | None | 2008, COVID, Flash Crash, etc. |
+| Online Learning | Static | Adaptive with Drift Detection |
+| Dashboard | Console print | Gradio Live Dashboard |
+## 🏗 Architecture
+```
+┌─────────────────────────────────────────────────────────────┐
+│                    A L P H A F O R G E                       │
+│                   Autonomous Quant Fund OS                   │
+├─────────────────┬──────────────────┬────────────────────────┤
+│   DATA LAYER    │   MODEL LAYER    │   EXECUTION LAYER      │
+│                 │                  │                         │
+│  Market Data    │  Alpha Ensemble  │  Portfolio Optimizer   │
+│  (OHLCV)        │  (LSTM+Trans+    │  (Mean-Var, Max Sharpe,│
+│       │         │   XGBoost)       │   Robust, Black-Lit)   │
+│       ▼         │       │          │         │              │
+│  Technical      │  Sentiment Model │  Backtest Engine       │
+│  Indicators     │  (FinBERT)       │  (PnL, Sharpe, Metrics)│
+│       │         │       │          │         │              │
+│       ▼         │       ▼          │         ▼              │
+│  Cross-Asset    │  Meta-Model      │  Strategy Ensemble     │
+│  Features       │  (Signal Weights) │  (Dynamic Allocation) │
+│                 │                  │                         │
+├─────────────────┼──────────────────┼────────────────────────┤
+│  RISK LAYER     │  ADVANCED ML     │  MONITORING LAYER     │
+│                 │                  │                         │
+│  Regime Detect  │  Online Learning │  Live Dashboard        │
+│  (HMM)          │  (Adaptive AI)   │  (Gradio)              │
+│       │         │       │          │         │              │
+│       ▼         │       ▼          │         ▼              │
+│  Risk Engine    │  Explainability  │  Factor Attribution    │
+│  (VaR/CVaR)     │  (SHAP)          │  (Decomposition)       │
+│       │         │       │          │         │              │
+│       ▼         │       ▼          │         ▼              │
+│  Stress Test    │  Anomaly Detect  │  Hedging Engine        │
+│  Engine         │  (IsoForest+AE)  │  (Options-based)       │
+│                 │                  │                         │
+│  Drawdown Ctrl  │  Bayesian Layer  │  Options Pricer        │
+│  (Scaling)      │  (Uncertainty)   │  (NN + Mispricing)     │
+└─────────────────┴──────────────────┴────────────────────────┘
 ```
+## 📦 Modules (22 files)
+### Core Pipeline (Papers-backed)
+| # | Module | File | Description |
+|---|--------|------|-------------|
+| 1 | **Alpha Model** | `alpha_model.py` | LSTM + Transformer + XGBoost ensemble |
+| 2 | **Sentiment** | `sentiment_model.py` | FinBERT pipeline (`ProsusAI/finbert`) |
+| 3 | **Volatility** | `volatility_model.py` | GARCH(1,1) + LSTM with skewed-t distribution |
+| 4 | **Portfolio** | `portfolio_optimizer.py` | MV, Max Sharpe, Min Vol, Robust, Black-Litterman |
+| 5 | **Options** | `options_pricer.py` | 4-layer NN pricing + IV + mispricing signals |
+| 6 | **Backtest** | `backtest_engine.py` | Full metrics (Sharpe, Sortino, Calmar, IC) |
+| 7 | **Data** | `market_data.py` | Fetch + 20+ technical indicators |
+### 🔥 High-Value Additions
+| # | Module | File | Description |
+|---|--------|------|-------------|
+| 8 | **Meta-Model** | `meta_model.py` | Learns which model to trust (Renaissance-style) |
+| 9 | **Regime HMM** | `regime_detector.py` | Hidden Markov Model + strategy switching |
+| 10 | **Risk Engine** | `risk_engine.py` | VaR (historical/parametric/Cornish-Fisher), CVaR, tail |
+| 11 | **Factor Decomp** | `factor_decomposition.py` | Momentum, Value, Size, Vol, Quality factors |
+| 12 | **Online Learning** | `online_learning.py` | Incremental SGD + concept drift detection |
+| 13 | **Explainability** | `explainability.py` | SHAP-style feature importance |
+| 14 | **Anomaly Det.** | `anomaly_detector.py` | Isolation Forest + Autoencoder |
+| 15 | **Stress Test** | `stress_test.py` | 2008, COVID, Flash Crash, Monte Carlo |
+| 16 | **Bayesian** | `bayesian_layer.py` | Probabilistic forecasts + shrinkage |
+| 17 | **Hedging** | `hedging_engine.py` | Delta-neutral dynamic hedging |
+| 18 | **Strategy Ensemble** | `strategy_ensemble.py` | Multi-strategy capital allocation |
+| 19 | **Drawdown Ctrl** | `risk_engine.py` | Adaptive position scaling |
+| 20 | **Orchestrator** | `main.py` | Wires everything together |
+| 21 | **Original** | `main_original.py` | Original modular main script |
+## 🚀 Quick Start
+```bash
+git clone https://huggingface.co/Premchan369/alphaforge-quant-system
+cd alphaforge-quant-system
+pip install -r requirements.txt
+# Run the full pipeline
+python main.py --tickers SPY QQQ AAPL MSFT GOOGL AMZN META NVDA TSLA JPM \
+               --start 2020-01-01 --end 2024-01-01 \
+               --epochs 30 --capital 1000000
 ```
+## 📊 Dashboard
+Live monitoring dashboard at: **https://huggingface.co/spaces/Premchan369/alphaforge-dashboard**
+Features:
+- Portfolio equity curve with drawdown
+- Live PnL and risk metrics
+- Covariance matrix heatmap
+- Factor exposure breakdown
+- Options IV surface
+- Anomaly detection tracker
+- Model performance comparison
+- Configuration panel
+## 📈 Key Metrics Tracked
+| Metric | Description | Where |
+|--------|-------------|-------|
+| Sharpe Ratio | Risk-adjusted return | Backtest |
+| Sortino Ratio | Downside risk-adjusted | Backtest |
+| Max Drawdown | Peak-to-trough decline | Risk Engine |
+| Calmar Ratio | Return / Max DD | Backtest |
+| VaR (95%, 99%) | Value at Risk | Risk Engine |
+| CVaR | Conditional VaR | Risk Engine |
+| IC | Information Coefficient | Alpha Model |
+| Alpha / Beta | Market-adjusted metrics | Factor Decomp |
+| Factor Exposures | Style factor loadings | Factor Decomp |
+| Win Rate | % of profitable days | Backtest |
+| Hedge Ratio | Delta hedge level | Hedging |
+## 🧠 Research Backing
+- **Alpha**: xLSTM-TS (Lopez Gil et al., 2024) + QuantaAlpha (Han et al., 2026)
+- **Sentiment**: FinBERT (Araci, 2019), ChatGPT benchmarking (Fatouros et al., 2023)
+- **Volatility**: LSTM-SSTD (Michankow, 2025)
+- **Portfolio**: MTL-TSMOM (Ong & Herremans, 2023)
+- **Options**: Feed-Forward NN (Berger et al., 2023), PINN (Dhiman et al., 2023)
+## 🏆 Real-World Alignment
+This system mirrors production architectures used by:
+- **Renaissance Technologies**: Multi-signal meta-model
+- **Two Sigma**: ML-driven alpha + risk decomposition
+- **Bridgewater**: Regime-based allocation
+- **AQR**: Factor decomposition + systematic strategies
+- **Citadel**: Options pricing + delta hedging
+## 📄 License
 MIT