Strategy Type
Machine Learning Trading Algorithms
Open-Source ML Models for Quantitative Finance
Machine learning trading algorithms apply statistical learning models. Gradient boosting, neural networks, and transformers. To financial time-series data to predict price movements or generate trading signals. These open-source implementations cover both regression (price target) and classification (direction) formulations.
12 algorithms2 libraries
Algorithm Network
How ML algorithms connect across libraries
ML Algorithms
Freqtrade9 algos
Microsoft Qlib6 algos
LightGBMRegressorintermediate
LightGBMClassifierintermediate
XGBoostRegressorintermediate
XGBoostClassifierintermediate
PyTorchMLPRegressoradvanced
PyTorchTransformerRegressoradvanced
LGBModelintermediate
XGBModelintermediate
DNNModeladvanced
ALSTMadvanced
TFTModeladvanced
GATsadvanced
Trading Decision Pipeline
How ML algorithms work together in a trading system
1
Market Data Input
Price, volume, indicators
OHLCV price data
Technical indicators
Feature engineering
2
ML Signal Generation
Model predictions
LightGBM/XGBoost regression
Transformer sequence modeling
MLP classification
3
Entry Decision
Signal threshold filtering
Confidence score > 0.6
Direction: Long/Short
4
Exit Strategy
Profit taking & stop loss
Take profit (fixed % or trailing)
Stop loss (ATR-based)
5
Risk Management
Position sizing & portfolio
Position sizing (Kelly criterion)
Portfolio rebalancing
Algorithm Comparison
Compare ML algorithms across key dimensions
Algorithm Comparison MatrixClick a column to expand details
| Metric | LightGBMRegressorFreqtrade | LightGBMClassifierFreqtrade | XGBoostRegressorFreqtrade | XGBoostClassifierFreqtrade | PyTorchMLPRegressorFreqtrade | PyTorchTransformerRegressorFreqtrade | LGBModelQlib (Microsoft) | XGBModelQlib (Microsoft) | DNNModelQlib (Microsoft) | ALSTMQlib (Microsoft) | TFTModelQlib (Microsoft) | GATsQlib (Microsoft) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Complexity | βββintermediate | βββintermediate | βββintermediate | βββintermediate | ββββadvanced | ββββadvanced | βββintermediate | βββintermediate | ββββadvanced | ββββadvanced | ββββadvanced | ββββadvanced |
| Prediction Type | Regression | Classification | Regression | Classification | Regression | Regression | Mixed | Mixed | Mixed | Sequence | Mixed | Mixed |
| Training Speed | β‘β‘β‘ | β‘β‘β‘ | β‘β‘β‘ | β‘β‘β‘ | β‘β‘ | β‘ | β‘β‘ | β‘β‘ | β‘β‘ | β‘ | β‘β‘ | β‘β‘ |
| Accuracy | πππ | πππ | πππ | πππ | πππ | ππππ | ππ | ππ | ππ | πππ | ππ | ππππ |
| Best For | Tabular data | Tabular data | Tabular data | Tabular data | Non-linear patterns | Time series patterns | General purpose | General purpose | General purpose | Sequential data | General purpose | Graph relationships |
Freqtrade
Gradient boosting regression model for price movement prediction using LightGBM.
Source:
freqtrade/freqai/prediction_models/LightGBMRegressor.pyLightGBM classification model for user-defined discrete labels.
Source:
freqtrade/freqai/prediction_models/LightGBMClassifier.pyXGBoost-based regression model for continuous value prediction.
Source:
freqtrade/freqai/prediction_models/XGBoostRegressor.pyXGBoost classification model for user-defined discrete labels.
Source:
freqtrade/freqai/prediction_models/XGBoostClassifier.pyMulti-layer perceptron neural network for regression-based price prediction.
Source:
freqtrade/freqai/prediction_models/PyTorchMLPRegressor.pyQlib (Microsoft)
LightGBM model for stock return prediction using technical and fundamental features.
Key Parameters
| num_leaves | 31 | Maximum number of leaves |
| learning_rate | 0.1 | Boosting learning rate |
Source:
qlib/contrib/model/gbdt.pyXGBoost model for stock return prediction.
Source:
qlib/contrib/model/xgboost.pyDeep neural network for nonlinear feature extraction and return prediction.
Key Parameters
| hidden_size | 256 | Hidden layer size |
Source:
qlib/contrib/model/pytorch_nn.pyAttention-based LSTM for sequential stock data modeling with attention mechanism.
Key Parameters
| hidden_size | 64 | LSTM hidden size |
| num_layers | 2 | Number of LSTM layers |
Source:
qlib/contrib/model/pytorch_alstm.pyTemporal Fusion Transformer combining static and temporal features for multi-horizon prediction.
Source:
qlib/contrib/model/pytorch_tft.pyMachine Learning Trading Algorithms, Algorithm Reference
- LightGBMRegressor (Freqtrade)
- Gradient boosting regression model for price movement prediction using LightGBM. Source: https://github.com/freqtrade/freqtrade/blob/c0a991f5632cb900075ff2864b6671ed71a319d7/freqtrade/freqai/prediction_models/LightGBMRegressor.py.
- LightGBMClassifier (Freqtrade)
- LightGBM classification model for user-defined discrete labels. Source: https://github.com/freqtrade/freqtrade/blob/c0a991f5632cb900075ff2864b6671ed71a319d7/freqtrade/freqai/prediction_models/LightGBMClassifier.py.
- XGBoostRegressor (Freqtrade)
- XGBoost-based regression model for continuous value prediction. Source: https://github.com/freqtrade/freqtrade/blob/c0a991f5632cb900075ff2864b6671ed71a319d7/freqtrade/freqai/prediction_models/XGBoostRegressor.py.
- XGBoostClassifier (Freqtrade)
- XGBoost classification model for user-defined discrete labels. Source: https://github.com/freqtrade/freqtrade/blob/c0a991f5632cb900075ff2864b6671ed71a319d7/freqtrade/freqai/prediction_models/XGBoostClassifier.py.
- PyTorchMLPRegressor (Freqtrade)
- Multi-layer perceptron neural network for regression-based price prediction. Source: https://github.com/freqtrade/freqtrade/blob/c0a991f5632cb900075ff2864b6671ed71a319d7/freqtrade/freqai/prediction_models/PyTorchMLPRegressor.py.
- PyTorchTransformerRegressor (Freqtrade)
- Transformer architecture for time-series regression using self-attention mechanism. Source: https://github.com/freqtrade/freqtrade/blob/c0a991f5632cb900075ff2864b6671ed71a319d7/freqtrade/freqai/prediction_models/PyTorchTransformerRegressor.py.
- LGBModel (Qlib (Microsoft))
- LightGBM model for stock return prediction using technical and fundamental features. Key parameters: num_leaves (Maximum number of leaves), learning_rate (Boosting learning rate).Source: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/gbdt.py.
- XGBModel (Qlib (Microsoft))
- XGBoost model for stock return prediction. Source: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/xgboost.py.
- DNNModel (Qlib (Microsoft))
- Deep neural network for nonlinear feature extraction and return prediction. Key parameters: hidden_size (Hidden layer size).Source: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_nn.py.
- ALSTM (Qlib (Microsoft))
- Attention-based LSTM for sequential stock data modeling with attention mechanism. Key parameters: hidden_size (LSTM hidden size), num_layers (Number of LSTM layers).Source: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_alstm.py.
- TFTModel (Qlib (Microsoft))
- Temporal Fusion Transformer combining static and temporal features for multi-horizon prediction. Source: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_tft.py.
- GATs (Qlib (Microsoft))
- Graph Attention Networks modeling stock relationships for cross-stock prediction. Source: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_gats.py.