| Pairs Trading (Cointegration & z-score) | Mean Reversion | Key model: Pairs Trading | Equities | Intraday | 2.33 | 1.19 | -0.25 | 0.14 | 31 | 10 | 8 | 16 | Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA; PyTorch; CUDA; cuDNN | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Pairs Trading (Kalman Filter) | Mean Reversion | Key model: Pairs Trading | Equities | Intraday | 0.87 | 1.84 | -0.21 | 0.1 | 37 | 10 | 8 | 16 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; TA-Lib; vectorbt; Numba; Ray; Dask for parallelism | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Index Mean Reversion (Bollinger Bands) | Mean Reversion | Key model: Index Mean Reversion | Equities | Swing | 2.74 | 1.12 | -0.15 | 0.23 | 46 | 4 | 4 | 11 | Numba; Ray; Dask for parallelism; Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; statsmodels; Backtrader | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| ETF Mean Reversion Rotation | Mean Reversion | Key model: ETF Mean Reversion Rotation | ETFs | Swing | 1.71 | 2.32 | -0.24 | 0.15 | 27 | 7 | 7 | 9 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| FX Range Reversion (RSI) | Mean Reversion | Key model: FX Range Reversion | Forex | Intraday | 2.79 | 3.2 | -0.14 | 0.2 | 29 | 0 | 8 | 11 | Numba; Ray; Dask for parallelism; Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; statsmodels; Backtrader | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Scales on multi-core; GPU optional |
| Crypto Market-Making (Spread Reversion) | Mean Reversion | Key model: Crypto Market-Making | Crypto | High-frequency | 2.88 | 2.39 | -0.22 | 0.25 | 35 | 5 | 5 | 11 | Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; statsmodels; Backtrader | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Commodities Calendar Spread Reversion | Mean Reversion | Key model: Commodities Calendar Spread Reversion | Commodities | Swing | 2.08 | 1.93 | -0.22 | 0.15 | 60 | 3 | 8 | 13 | Numba; Ray; Dask for parallelism; Python; pandas; numpy; statsmodels; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Intraday VWAP Reversion | Mean Reversion | Key model: Intraday VWAP Reversion | Equities | Intraday | 2.73 | 2.46 | -0.29 | 0.26 | 45 | 3 | 8 | 15 | PyTorch; CUDA; cuDNN; Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Bid-Ask Bounce Reversion | Mean Reversion | Key model: Bid-Ask Bounce Reversion | Equities | High-frequency | 1.44 | 1.94 | -0.2 | 0.15 | 52 | 9 | 6 | 13 | Python; pandas; numpy; TA-Lib; vectorbt; Numba; Ray; Dask for parallelism; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Stat-Arb Sector-Neutral Mean Reversion | Mean Reversion | Key model: Stat-Arb Sector-Neutral Mean Reversion | Equities | Intraday | 1.02 | 1.26 | -0.28 | 0.21 | 52 | 9 | 3 | 14 | PyTorch; CUDA; cuDNN; TensorFlow/Keras; CUDA; Numba; Ray; Dask for parallelism | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Time-Series Momentum (12M lookback) | Momentum / Trend | Key model: Time-Series Momentum | Multi-Asset (Futures) | Monthly | 1.38 | 1.85 | -0.35 | 0.18 | 31 | 8 | 4 | 15 | Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; statsmodels; Backtrader; Numba; Ray; Dask for parallelism | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Cross-Sectional Momentum (Equities) | Momentum / Trend | Key model: Cross-Sectional Momentum | Equities | Monthly | 0.73 | 0.9 | -0.23 | 0.18 | 26 | 2 | 6 | 6 | Numba; Ray; Dask for parallelism; Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Dual Momentum (Equity/Bond Rotation) | Momentum / Trend | Key model: Dual Momentum | ETFs | Monthly | 0.72 | 1.74 | -0.26 | 0.19 | 26 | 0 | 6 | 10 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader; Zipline; Qlib; Backtrader | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Scales on multi-core; GPU optional |
| ADX Trend Following (Futures) | Momentum / Trend | Key model: ADX Trend Following | Futures | Swing | 1.3 | 1.81 | -0.3 | 0.09 | 28 | 1 | 2 | 12 | Numba; Ray; Dask for parallelism; Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Turtle Breakout (ATR position) | Momentum / Trend | Key model: Turtle Breakout | Futures | Swing | 0.7 | 1.42 | -0.26 | 0.12 | 29 | 6 | 3 | 13 | Numba; Ray; Dask for parallelism; Zipline; Qlib; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Commodity Trend (managed futures) | Momentum / Trend | Key model: Commodity Trend | Futures | Monthly | 0.92 | 1.64 | -0.29 | 0.21 | 24 | 1 | 3 | 8 | Python; pandas; numpy; statsmodels; Backtrader; Python; sklearn; xgboost; lightgbm; Numba; Ray; Dask for parallelism | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| FX Trend (time-series) | Momentum / Trend | Key model: FX Trend | Forex | Monthly | 1.07 | 0.91 | -0.23 | 0.09 | 12 | 0 | 4 | 6 | TensorFlow/Keras; CUDA; Python; pandas; numpy; TA-Lib; vectorbt; Python; sklearn; xgboost; lightgbm | Intraday kill-switch; regime filters; drawdown-based de-risking | Scales on multi-core; GPU optional |
| Crypto Trend (breakouts) | Momentum / Trend | Key model: Crypto Trend | Crypto | Swing | 0.77 | 1.05 | -0.19 | 0.16 | 25 | 3 | 5 | 11 | Python; pandas; numpy; TA-Lib; vectorbt; Python; pandas; numpy; statsmodels; Backtrader; Zipline; Qlib; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Moving Average Crossover (50/200) | Momentum / Trend | Key model: Moving Average Crossover | Equities | Positional | 0.88 | 1.35 | -0.2 | 0.09 | 30 | 10 | 2 | 5 | PyTorch; CUDA; cuDNN; Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| ETF Momentum Rotation | Momentum / Trend | Key model: ETF Momentum Rotation | ETFs | Monthly | 0.8 | 1.11 | -0.27 | 0.14 | 18 | 7 | 3 | 6 | PyTorch; CUDA; cuDNN; TensorFlow/Keras; CUDA; Python; pandas; numpy; statsmodels; Backtrader | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| "Risk Parity (Naive | inverse vol)" | Factor / Asset Allocation | Key model: Risk Parity | Multi-Asset | Monthly | 0.99 | 1.28 | -0.28 | 0.08 | 20 | 1 | 3 | 9 | PyTorch; CUDA; cuDNN; Numba; Ray; Dask for parallelism; Python; pandas; numpy; TA-Lib; vectorbt | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Equal Risk Contribution (ERC) | Factor / Asset Allocation | Key model: Equal Risk Contribution | Multi-Asset | Monthly | 1.14 | 1.02 | -0.28 | 0.11 | 20 | 3 | 4 | 9 | Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Maximum Diversification | Factor / Asset Allocation | Key model: Maximum Diversification | Multi-Asset | Monthly | 0.69 | 1.11 | -0.13 | 0.12 | 16 | 0 | 4 | 3 | Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA; PyTorch; CUDA; cuDNN | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Scales on multi-core; GPU optional |
| Value Factor Long-Short | Factor / Asset Allocation | Key model: Value Factor Long-Short | Equities | Monthly | 0.63 | 1.26 | -0.14 | 0.08 | 9 | 5 | 3 | 9 | Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA; Python; pandas; numpy; TA-Lib; vectorbt | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Quality Factor Long-Short | Factor / Asset Allocation | Key model: Quality Factor Long-Short | Equities | Monthly | 0.97 | 1.19 | -0.19 | 0.12 | 12 | 1 | 4 | 6 | Python; sklearn; xgboost; lightgbm; PyTorch; CUDA; cuDNN; Python; pandas; numpy; TA-Lib; vectorbt | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Low Volatility Factor | Factor / Asset Allocation | Key model: Low Volatility Factor | Equities | Monthly | 0.87 | 1.55 | -0.13 | 0.07 | 17 | 4 | 2 | 4 | TensorFlow/Keras; CUDA; Python; pandas; numpy; TA-Lib; vectorbt; Numba; Ray; Dask for parallelism | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Size (SMB) Factor Tilt | Factor / Asset Allocation | Key model: Size | Equities | Monthly | 0.68 | 1.14 | -0.27 | 0.09 | 12 | 1 | 5 | 7 | TensorFlow/Keras; CUDA; Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Multi-Factor (Value+Momentum) | Factor / Asset Allocation | Key model: Multi-Factor | Equities | Monthly | 1.0 | 1.29 | -0.13 | 0.08 | 10 | 2 | 2 | 4 | Zipline; Qlib; Backtrader; TensorFlow/Keras; CUDA; Python; pandas; numpy; TA-Lib; vectorbt | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| ESG Factor Tilt | Factor / Asset Allocation | Key model: ESG Factor Tilt | Equities | Quarterly | 0.77 | 1.05 | -0.23 | 0.13 | 12 | 4 | 5 | 7 | Numba; Ray; Dask for parallelism; Python; pandas; numpy; statsmodels; Backtrader; Zipline; Qlib; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Minimum Variance Portfolio | Factor / Asset Allocation | Key model: Minimum Variance Portfolio | Multi-Asset | Monthly | 1.1 | 0.93 | -0.23 | 0.08 | 12 | 1 | 5 | 9 | TensorFlow/Keras; CUDA; Python; pandas; numpy; statsmodels; Backtrader; Zipline; Qlib; Backtrader | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Volatility Risk Premium (short ATM straddle + hedge) | Options / Volatility | Key model: Volatility Risk Premium | Options | Monthly | 1.36 | 1.83 | -0.41 | 0.09 | 38 | 18 | 8 | 10 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; TA-Lib; vectorbt; Python; pandas; numpy; statsmodels; Backtrader | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Put Write (cash-secured) | Options / Volatility | Key model: Put Write | Options | Monthly | 0.96 | 2.12 | -0.19 | 0.09 | 37 | 6 | 9 | 11 | Zipline; Qlib; Backtrader; Python; pandas; numpy; statsmodels; Backtrader; Python; sklearn; xgboost; lightgbm | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Covered Call Overlay | Options / Volatility | Key model: Covered Call Overlay | Options | Monthly | 1.38 | 1.9 | -0.2 | 0.12 | 25 | 25 | 10 | 10 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Long Convexity (tail hedge) | Options / Volatility | Key model: Long Convexity | Options | Positional | 1.25 | 1.49 | -0.27 | 0.21 | 30 | 8 | 5 | 20 | Zipline; Qlib; Backtrader; Python; pandas; numpy; statsmodels; Backtrader; PyTorch; CUDA; cuDNN | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Gamma Scalping (delta-neutral) | Options / Volatility | Key model: Gamma Scalping | Options | Intraday | 1.3 | 1.27 | -0.23 | 0.16 | 34 | 26 | 10 | 11 | Python; pandas; numpy; TA-Lib; vectorbt; Python; pandas; numpy; statsmodels; Backtrader; Numba; Ray; Dask for parallelism | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Variance Swap Carry | Options / Volatility | Key model: Variance Swap Carry | Options | Monthly | 0.93 | 2.04 | -0.19 | 0.13 | 47 | 12 | 9 | 16 | Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; statsmodels; Backtrader; Zipline; Qlib; Backtrader | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Calendar Spread (vol term structure) | Options / Volatility | Key model: Calendar Spread | Options | Monthly | 0.82 | 2.16 | -0.38 | 0.1 | 42 | 11 | 9 | 20 | Python; sklearn; xgboost; lightgbm; PyTorch; CUDA; cuDNN; TensorFlow/Keras; CUDA | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Skew Carry (risk reversal) | Options / Volatility | Key model: Skew Carry | Options | Monthly | 0.97 | 1.69 | -0.38 | 0.21 | 15 | 16 | 10 | 16 | Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism; Python; pandas; numpy; TA-Lib; vectorbt | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Collar Overlay | Options / Volatility | Key model: Collar Overlay | Options | Monthly | 1.0 | 2.14 | -0.2 | 0.19 | 22 | 23 | 6 | 16 | Python; sklearn; xgboost; lightgbm; Zipline; Qlib; Backtrader; PyTorch; CUDA; cuDNN | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Strangle Sell with Dynamic Hedges | Options / Volatility | Key model: Strangle Sell with Dynamic Hedges | Options | Monthly | 0.98 | 1.35 | -0.42 | 0.16 | 39 | 21 | 9 | 10 | TensorFlow/Keras; CUDA; Numba; Ray; Dask for parallelism; Python; sklearn; xgboost; lightgbm | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| G10 FX Carry (dollar-based) | FX / Rates | Key model: G10 FX Carry | Forex | Monthly | 0.83 | 0.8 | -0.29 | 0.11 | 18 | 7 | 5 | 10 | Zipline; Qlib; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Dollar-Neutral FX Carry | FX / Rates | Key model: Dollar-Neutral FX Carry | Forex | Monthly | 0.98 | 1.57 | -0.2 | 0.14 | 17 | 8 | 6 | 8 | Python; pandas; numpy; statsmodels; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt; Python; sklearn; xgboost; lightgbm | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| FX Momentum (ranked forward discount) | FX / Rates | Key model: FX Momentum | Forex | Monthly | 0.98 | 0.92 | -0.34 | 0.18 | 10 | 7 | 5 | 6 | Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism; PyTorch; CUDA; cuDNN | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Bond Futures Carry | FX / Rates | Key model: Bond Futures Carry | Bonds | Monthly | 0.74 | 0.92 | -0.21 | 0.17 | 11 | 6 | 3 | 5 | Numba; Ray; Dask for parallelism; Zipline; Qlib; Backtrader; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Butterfly (yield curve) | FX / Rates | Key model: Butterfly | Rates | Monthly | 0.53 | 1.0 | -0.18 | 0.11 | 22 | 8 | 6 | 8 | Numba; Ray; Dask for parallelism; PyTorch; CUDA; cuDNN; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Term Structure (roll-down) | FX / Rates | Key model: Term Structure | Bonds | Monthly | 1.0 | 1.24 | -0.17 | 0.15 | 23 | 7 | 4 | 6 | Numba; Ray; Dask for parallelism; Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Cross-Currency Basis Capture | FX / Rates | Key model: Cross-Currency Basis Capture | Forex | Monthly | 0.88 | 1.02 | -0.33 | 0.09 | 16 | 5 | 4 | 4 | Python; pandas; numpy; TA-Lib; vectorbt; Numba; Ray; Dask for parallelism; Zipline; Qlib; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| FX Value (PPP deviations) | FX / Rates | Key model: FX Value | Forex | Monthly | 0.92 | 1.37 | -0.34 | 0.11 | 25 | 7 | 5 | 3 | Python; pandas; numpy; TA-Lib; vectorbt; PyTorch; CUDA; cuDNN; Zipline; Qlib; Backtrader | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Sovereign Spread Carry (EM) | FX / Rates | Key model: Sovereign Spread Carry | Bonds | Monthly | 1.01 | 1.41 | -0.27 | 0.06 | 19 | 4 | 5 | 9 | TensorFlow/Keras; CUDA; Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Futures Basis (commodities) | FX / Rates | Key model: Futures Basis | Commodities | Monthly | 0.79 | 1.02 | -0.25 | 0.11 | 20 | 2 | 5 | 5 | TensorFlow/Keras; CUDA; Numba; Ray; Dask for parallelism; Python; pandas; numpy; statsmodels; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Random Forest (cross-sectional alpha) | Machine Learning | Key model: Random Forest | Equities | Daily | 1.23 | 2.06 | -0.31 | 0.18 | 54 | 16 | 6 | 10 | PyTorch; CUDA; cuDNN; Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; TA-Lib; vectorbt | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Gradient Boosting / XGBoost | Machine Learning | Key model: Gradient Boosting / XGBoost | Equities | Daily | 0.99 | 2.22 | -0.26 | 0.24 | 51 | 21 | 7 | 13 | Python; pandas; numpy; statsmodels; Backtrader; Zipline; Qlib; Backtrader; TensorFlow/Keras; CUDA | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| CatBoost Alpha Model | Machine Learning | Key model: CatBoost Alpha Model | Equities | Daily | 1.6 | 1.56 | -0.21 | 0.24 | 66 | 7 | 6 | 9 | Python; pandas; numpy; TA-Lib; vectorbt; Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Neural Net (MLP) Classification | Machine Learning | Key model: Neural Net | Equities | Daily | 0.91 | 1.76 | -0.3 | 0.27 | 54 | 49 | 10 | 18 | Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; TA-Lib; vectorbt; TensorFlow/Keras; CUDA | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| LSTM Sequence Model (alpha timing) | Machine Learning | Key model: LSTM Sequence Model | Equities | Daily | 1.4 | 1.26 | -0.27 | 0.2 | 44 | 41 | 16 | 20 | PyTorch; CUDA; cuDNN; Numba; Ray; Dask for parallelism; Python; pandas; numpy; TA-Lib; vectorbt | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| TabNet / DL Tabular Alpha | Machine Learning | Key model: TabNet / DL Tabular Alpha | Equities | Daily | 1.23 | 2.33 | -0.28 | 0.23 | 44 | 59 | 16 | 15 | Numba; Ray; Dask for parallelism; Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Autoencoder Regime Features + Linear Head | Machine Learning | Key model: Autoencoder Regime Features + Linear Head | Multi-Asset | Daily | 1.01 | 1.69 | -0.26 | 0.19 | 46 | 5 | 12 | 19 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader; Numba; Ray; Dask for parallelism | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Graph NN (sector relations) | Machine Learning | Key model: Graph NN | Equities | Daily | 1.27 | 2.33 | -0.2 | 0.18 | 71 | 38 | 16 | 10 | TensorFlow/Keras; CUDA; Numba; Ray; Dask for parallelism; PyTorch; CUDA; cuDNN | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| LightGBM Feature Importance Alpha | Machine Learning | Key model: LightGBM Feature Importance Alpha | Equities | Daily | 1.09 | 2.17 | -0.27 | 0.25 | 30 | 22 | 13 | 9 | Numba; Ray; Dask for parallelism; PyTorch; CUDA; cuDNN; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Sklearn Stacking Ensemble | Machine Learning | Key model: Sklearn Stacking Ensemble | Equities | Daily | 1.0 | 1.79 | -0.26 | 0.19 | 47 | 56 | 10 | 11 | Python; sklearn; xgboost; lightgbm; TensorFlow/Keras; CUDA; Numba; Ray; Dask for parallelism | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| DDPG Allocation (equities/bonds/commodities) | Reinforcement Learning | Key model: DDPG Allocation | Multi-Asset | Daily | 1.27 | 1.38 | -0.35 | 0.15 | 70 | 40 | 19 | 23 | Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism; PyTorch; CUDA; cuDNN | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| PPO Position Sizing (futures) | Reinforcement Learning | Key model: PPO Position Sizing | Futures | Daily | 1.57 | 1.19 | -0.35 | 0.2 | 54 | 57 | 15 | 24 | Python; sklearn; xgboost; lightgbm; PyTorch; CUDA; cuDNN; TensorFlow/Keras; CUDA | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| SAC Market Making (crypto) | Reinforcement Learning | Key model: SAC Market Making | Crypto | Intraday | 1.09 | 1.91 | -0.33 | 0.12 | 81 | 34 | 13 | 11 | Zipline; Qlib; Backtrader; TensorFlow/Keras; CUDA; Python; pandas; numpy; TA-Lib; vectorbt | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| A2C Hedging Policy (options delta) | Reinforcement Learning | Key model: A2C Hedging Policy | Options | Intraday | 0.94 | 1.97 | -0.24 | 0.26 | 68 | 46 | 9 | 14 | Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; TA-Lib; vectorbt; Numba; Ray; Dask for parallelism | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| QR-DQN Spread Trading | Reinforcement Learning | Key model: QR-DQN Spread Trading | Futures | Intraday | 1.03 | 2.42 | -0.37 | 0.09 | 38 | 80 | 12 | 12 | Zipline; Qlib; Backtrader; PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| AlphaZero-style Discrete Allocation | Reinforcement Learning | Key model: AlphaZero-style Discrete Allocation | ETFs | Daily | 1.33 | 1.94 | -0.3 | 0.11 | 38 | 42 | 15 | 11 | Numba; Ray; Dask for parallelism; Python; pandas; numpy; statsmodels; Backtrader; PyTorch; CUDA; cuDNN | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Meta-RL Regime Switching | Reinforcement Learning | Key model: Meta-RL Regime Switching | Multi-Asset | Daily | 0.78 | 2.26 | -0.39 | 0.11 | 71 | 48 | 9 | 15 | Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA; PyTorch; CUDA; cuDNN | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Policy Gradients Event-Driven | Reinforcement Learning | Key model: Policy Gradients Event-Driven | Equities | Intraday | 1.55 | 1.76 | -0.2 | 0.13 | 72 | 64 | 12 | 9 | TensorFlow/Keras; CUDA; Zipline; Qlib; Backtrader; Python; pandas; numpy; statsmodels; Backtrader | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| RL for Execution (TWAP/VWAP) | Reinforcement Learning | Key model: RL for Execution | Equities | High-frequency | 1.39 | 1.53 | -0.38 | 0.12 | 70 | 19 | 10 | 8 | PyTorch; CUDA; cuDNN; Numba; Ray; Dask for parallelism; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| PPO Volatility Targeting | Reinforcement Learning | Key model: PPO Volatility Targeting | Multi-Asset | Daily | 1.02 | 1.46 | -0.24 | 0.21 | 64 | 19 | 18 | 15 | Python; sklearn; xgboost; lightgbm; Zipline; Qlib; Backtrader; TensorFlow/Keras; CUDA | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Earnings Announcement Premium (expected announcers) | Event-Driven / Alt-Data | Key model: Earnings Announcement Premium | Equities | Monthly | 1.14 | 1.81 | -0.22 | 0.25 | 24 | 2 | 4 | 8 | Numba; Ray; Dask for parallelism; Python; sklearn; xgboost; lightgbm; TensorFlow/Keras; CUDA | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Post-Earnings Drift (PEAD) | Event-Driven / Alt-Data | Key model: Post-Earnings Drift | Equities | Daily | 1.15 | 1.71 | -0.27 | 0.16 | 32 | 16 | 8 | 13 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Analyst Revisions Momentum | Event-Driven / Alt-Data | Key model: Analyst Revisions Momentum | Equities | Daily | 1.51 | 2.05 | -0.22 | 0.1 | 29 | 21 | 10 | 15 | TensorFlow/Keras; CUDA; Python; pandas; numpy; statsmodels; Backtrader; Python; sklearn; xgboost; lightgbm | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| M&A Rumor/News Spread | Event-Driven / Alt-Data | Key model: M&A Rumor/News Spread | Equities | Intraday | 1.41 | 1.33 | -0.24 | 0.17 | 32 | 5 | 8 | 12 | Zipline; Qlib; Backtrader; PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Insider Trading Signal (public filings) | Event-Driven / Alt-Data | Key model: Insider Trading Signal | Equities | Positional | 1.08 | 1.53 | -0.21 | 0.24 | 36 | 13 | 9 | 13 | Python; sklearn; xgboost; lightgbm; Zipline; Qlib; Backtrader; PyTorch; CUDA; cuDNN | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Macro Surprise Index (Citi/DB proxies) | Event-Driven / Alt-Data | Key model: Macro Surprise Index | Multi-Asset | Monthly | 1.16 | 1.51 | -0.27 | 0.26 | 40 | 16 | 10 | 6 | Zipline; Qlib; Backtrader; TensorFlow/Keras; CUDA; PyTorch; CUDA; cuDNN | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Options Implied-Realized Spread | Event-Driven / Alt-Data | Key model: Options Implied-Realized Spread | Options | Monthly | 0.84 | 1.77 | -0.22 | 0.18 | 43 | 24 | 4 | 9 | Python; sklearn; xgboost; lightgbm; TensorFlow/Keras; CUDA; Python; pandas; numpy; TA-Lib; vectorbt | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Sentiment from News (NLP) | Event-Driven / Alt-Data | Key model: Sentiment from News | Equities | Daily | 1.15 | 2.01 | -0.3 | 0.26 | 53 | 25 | 5 | 17 | Python; pandas; numpy; TA-Lib; vectorbt; Python; sklearn; xgboost; lightgbm; TensorFlow/Keras; CUDA | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Weather Derivatives Trading | Event-Driven / Alt-Data | Key model: Weather Derivatives Trading | Derivatives | Monthly | 1.24 | 1.22 | -0.16 | 0.25 | 44 | 3 | 9 | 8 | PyTorch; CUDA; cuDNN; Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Shipping/Alt Activity (AIS) Factor | Event-Driven / Alt-Data | Key model: Shipping/Alt Activity | Equities | Monthly | 1.13 | 1.73 | -0.24 | 0.17 | 24 | 12 | 5 | 15 | TensorFlow/Keras; CUDA; Zipline; Qlib; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| X-Sectional Momentum (top vs bottom cap) | Crypto | Key model: X-Sectional Momentum | Crypto | Daily | 0.82 | 1.93 | -0.35 | 0.29 | 52 | 17 | 4 | 10 | Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Time-Series Momentum (alts vs BTC) | Crypto | Key model: Time-Series Momentum | Crypto | Daily | 1.29 | 1.48 | -0.33 | 0.17 | 68 | 34 | 10 | 13 | Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; TA-Lib; vectorbt; Zipline; Qlib; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Mean Reversion on Stablecoin Premiums | Crypto | Key model: Mean Reversion on Stablecoin Premiums | Crypto | Intraday | 0.79 | 1.91 | -0.44 | 0.25 | 65 | 24 | 10 | 16 | Numba; Ray; Dask for parallelism; Zipline; Qlib; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Funding Rate Carry (perpetuals) | Crypto | Key model: Funding Rate Carry | Crypto | Daily | 1.37 | 1.06 | -0.21 | 0.17 | 26 | 28 | 5 | 14 | PyTorch; CUDA; cuDNN; Python; pandas; numpy; statsmodels; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| On-chain Address Growth Factor | Crypto | Key model: On-chain Address Growth Factor | Crypto | Daily | 1.3 | 2.16 | -0.43 | 0.26 | 36 | 21 | 10 | 16 | Python; pandas; numpy; statsmodels; Backtrader; Python; sklearn; xgboost; lightgbm; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| ETH/BTC Ratio Trend | Crypto | Key model: ETH/BTC Ratio Trend | Crypto | Swing | 1.36 | 1.71 | -0.23 | 0.2 | 54 | 2 | 5 | 9 | Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism; Python; sklearn; xgboost; lightgbm | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Basis Arbitrage (futures spot) | Crypto | Key model: Basis Arbitrage | Crypto | High-frequency | 1.2 | 1.46 | -0.43 | 0.23 | 26 | 28 | 6 | 17 | Python; sklearn; xgboost; lightgbm; Python; pandas; numpy; statsmodels; Backtrader; Zipline; Qlib; Backtrader | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Liquidity Mining Yield + Hedge | Crypto | Key model: Liquidity Mining Yield + Hedge | Crypto | Daily | 1.24 | 1.28 | -0.36 | 0.13 | 53 | 26 | 6 | 8 | Python; pandas; numpy; TA-Lib; vectorbt; Python; pandas; numpy; statsmodels; Backtrader; TensorFlow/Keras; CUDA | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Staking Yield Rotation | Crypto | Key model: Staking Yield Rotation | Crypto | Positional | 1.1 | 1.21 | -0.22 | 0.13 | 49 | 40 | 8 | 13 | Python; sklearn; xgboost; lightgbm; Zipline; Qlib; Backtrader; Python; pandas; numpy; statsmodels; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Crypto Seasonality (month effects) | Crypto | Key model: Crypto Seasonality | Crypto | Positional | 1.32 | 1.78 | -0.41 | 0.19 | 42 | 37 | 8 | 16 | PyTorch; CUDA; cuDNN; Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| VWAP/TWAP Execution Alpha (slippage capture) | Market Microstructure / Execution | Key model: VWAP/TWAP Execution Alpha | Equities | High-frequency | 1.19 | 1.12 | -0.28 | 0.15 | 40 | 24 | 9 | 15 | Python; sklearn; xgboost; lightgbm; Zipline; Qlib; Backtrader; Numba; Ray; Dask for parallelism | Vol targeting; position sizing (Kelly cap); hard stop-loss; trailing stop; VaR/ES limits | Benefits from GPU; scales with VRAM |
| Opening Auction Imbalance Alpha | Market Microstructure / Execution | Key model: Opening Auction Imbalance Alpha | Equities | Intraday | 1.28 | 1.62 | -0.3 | 0.16 | 68 | 3 | 11 | 10 | Numba; Ray; Dask for parallelism; Python; pandas; numpy; TA-Lib; vectorbt; TensorFlow/Keras; CUDA | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Closing Auction Imbalance Alpha | Market Microstructure / Execution | Key model: Closing Auction Imbalance Alpha | Equities | Intraday | 0.75 | 1.11 | -0.31 | 0.19 | 67 | 8 | 5 | 16 | Zipline; Qlib; Backtrader; Python; pandas; numpy; statsmodels; Backtrader; Python; sklearn; xgboost; lightgbm | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Latency-Arbitrage Proxy (non-HFT) on crypto | Market Microstructure / Execution | Key model: Latency-Arbitrage Proxy | Crypto | High-frequency | 0.62 | 1.3 | -0.33 | 0.21 | 45 | 26 | 6 | 9 | Python; pandas; numpy; TA-Lib; vectorbt; TensorFlow/Keras; CUDA; Python; sklearn; xgboost; lightgbm | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |
| Queue Positioning (order book depth) | Market Microstructure / Execution | Key model: Queue Positioning | Equities | High-frequency | 1.18 | 1.18 | -0.21 | 0.15 | 43 | 21 | 5 | 13 | Python; pandas; numpy; statsmodels; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt; Zipline; Qlib; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Liquidity Provision (rebates + inventory control) | Market Microstructure / Execution | Key model: Liquidity Provision | Equities | High-frequency | 1.28 | 1.79 | -0.29 | 0.19 | 25 | 16 | 12 | 7 | PyTorch; CUDA; cuDNN; Python; sklearn; xgboost; lightgbm; Zipline; Qlib; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Tick Rule Micro-Momentum | Market Microstructure / Execution | Key model: Tick Rule Micro-Momentum | Equities | High-frequency | 1.18 | 1.93 | -0.33 | 0.11 | 26 | 35 | 9 | 15 | Python; pandas; numpy; TA-Lib; vectorbt; Zipline; Qlib; Backtrader; Python; pandas; numpy; statsmodels; Backtrader | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Order Flow Imbalance Mean Reversion | Market Microstructure / Execution | Key model: Order Flow Imbalance Mean Reversion | Futures | High-frequency | 1.24 | 1.23 | -0.28 | 0.1 | 27 | 19 | 11 | 7 | Python; pandas; numpy; statsmodels; Backtrader; Python; pandas; numpy; TA-Lib; vectorbt; TensorFlow/Keras; CUDA | Position sizing (vol parity); 2xATR stop; portfolio-level max DD circuit-breaker | Benefits from GPU; scales with VRAM |
| Spread/Vol Forecasted Reversion | Market Microstructure / Execution | Key model: Spread/Vol Forecasted Reversion | Futures | Intraday | 0.87 | 1.31 | -0.19 | 0.18 | 59 | 26 | 6 | 12 | Zipline; Qlib; Backtrader; Python; pandas; numpy; statsmodels; Backtrader; PyTorch; CUDA; cuDNN | Intraday kill-switch; regime filters; drawdown-based de-risking | Benefits from GPU; scales with VRAM |
| Intraday Regime Switch (micro alpha) | Market Microstructure / Execution | Key model: Intraday Regime Switch | Equities | Intraday | 1.26 | 1.21 | -0.23 | 0.11 | 53 | 15 | 9 | 7 | Zipline; Qlib; Backtrader; Python; sklearn; xgboost; lightgbm; TensorFlow/Keras; CUDA | Hedging overlays (index futures/options); daily risk budgeting; max leverage cap | Benefits from GPU; scales with VRAM |