Strategietyp
Trading-Algorithmen mit maschinellem Lernen
Open-Source-ML-Modelle für quantitative Finanzen
Trading-Algorithmen mit maschinellem Lernen wenden statistische Lernmodelle (Gradient Boosting, neuronale Netze, Transformer) auf Finanzzeitreihen an, um Kursbewegungen zu prognostizieren oder Handelssignale zu erzeugen. Diese Open-Source-Implementierungen decken sowohl Regressions- (Preisziel) als auch Klassifikations-Formulierungen (Richtung) ab.
13 Algorithmen2 Bibliotheken
Algorithmus-Netzwerk
Wie ML-Algorithmen über Bibliotheken hinweg verbunden sind
ML Algorithms
Freqtrade9 algos
Microsoft Qlib6 algos
LightGBMRegressorintermediate
LightGBMClassifierintermediate
XGBoostRegressorintermediate
XGBoostClassifierintermediate
CatboostRegressorintermediate
PyTorchMLPRegressoradvanced
PyTorchTransformerRegressoradvanced
LGBModelintermediate
XGBModelintermediate
DNNModeladvanced
ALSTMadvanced
TFTModeladvanced
GATsadvanced
Trading-Entscheidungs-Pipeline
Wie ML-Algorithmen in einem Trading-System zusammenarbeiten
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
Algorithmusvergleich
ML-Algorithmen über zentrale Dimensionen vergleichen
Algorithmus-VergleichsmatrixKlicken Sie auf eine Spalte für Details
| Kennzahl | LightGBMRegressorFreqtrade | LightGBMClassifierFreqtrade | XGBoostRegressorFreqtrade | XGBoostClassifierFreqtrade | CatboostRegressorFreqtrade | PyTorchMLPRegressorFreqtrade | PyTorchTransformerRegressorFreqtrade | LGBModelQlib (Microsoft) | XGBModelQlib (Microsoft) | DNNModelQlib (Microsoft) | ALSTMQlib (Microsoft) | TFTModelQlib (Microsoft) | GATsQlib (Microsoft) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Komplexität | ⭐⭐⭐intermediate | ⭐⭐⭐intermediate | ⭐⭐⭐intermediate | ⭐⭐⭐intermediate | ⭐⭐⭐intermediate | ⭐⭐⭐⭐advanced | ⭐⭐⭐⭐advanced | ⭐⭐⭐intermediate | ⭐⭐⭐intermediate | ⭐⭐⭐⭐advanced | ⭐⭐⭐⭐advanced | ⭐⭐⭐⭐advanced | ⭐⭐⭐⭐advanced |
| Vorhersagetyp | Regression | Klassifikation | Regression | Klassifikation | Regression | Regression | Regression | Gemischt | Gemischt | Gemischt | Sequenz | Gemischt | Gemischt |
| Trainingsgeschwindigkeit | ⚡⚡⚡ | ⚡⚡⚡ | ⚡⚡⚡ | ⚡⚡⚡ | ⚡⚡ | ⚡⚡ | ⚡ | ⚡⚡ | ⚡⚡ | ⚡⚡ | ⚡ | ⚡⚡ | ⚡⚡ |
| Genauigkeit | 📊📊📊 | 📊📊📊 | 📊📊📊 | 📊📊📊 | 📊📊📊 | 📊📊📊 | 📊📊📊📊 | 📊📊 | 📊📊 | 📊📊 | 📊📊📊 | 📊📊 | 📊📊📊📊 |
| Am besten für | Tabellarische Daten | Tabellarische Daten | Tabellarische Daten | Tabellarische Daten | Allzweck | Nichtlineare Muster | Zeitreihen-Muster | Allzweck | Allzweck | Allzweck | Sequenzielle Daten | Allzweck | Graph-Beziehungen |
Freqtrade
Gradient boosting regression model for price movement prediction using LightGBM.
Geschwindigkeit⚡⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| n_estimators | 1000 | Number of boosting rounds |
| learning_rate | 0.01 | Step size shrinkage |
Quelle:
freqai/prediction_models/LightGBMRegressor.pyGradient boosting classification model for directional prediction (up/down/neutral).
Geschwindigkeit⚡⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| n_estimators | 1000 | Number of boosting rounds |
Quelle:
freqai/prediction_models/LightGBMClassifier.pyXGBoost-based regression model for continuous value prediction.
Geschwindigkeit⚡⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| n_estimators | 1000 | Number of boosting rounds |
| max_depth | 6 | Maximum tree depth |
Quelle:
freqai/prediction_models/XGBoostRegressor.pyXGBoost-based classification model for directional prediction.
Geschwindigkeit⚡⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| n_estimators | 1000 | Number of boosting rounds |
Quelle:
freqai/prediction_models/XGBoostClassifier.pyCatBoost gradient boosting model with native categorical feature support.
Geschwindigkeit⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| iterations | 1000 | Number of boosting iterations |
Quelle:
freqai/prediction_models/CatboostRegressor.pyMulti-layer perceptron neural network for regression-based price prediction.
Geschwindigkeit⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| hidden_dim | 128 | Hidden layer dimension |
| dropout_percent | 0.2 | Dropout rate |
Quelle:
freqai/prediction_models/PyTorchMLPRegressor.pyTransformer architecture for time-series regression using self-attention mechanism.
Geschwindigkeit⚡
Genauigkeit📊📊📊📊
Schlüsselparameter
| num_heads | 8 | Number of attention heads |
| num_layers | 2 | Number of transformer layers |
Quelle:
freqai/prediction_models/PyTorchTransformerRegressor.pyQlib (Microsoft)
LightGBM model for stock return prediction using technical and fundamental features.
Geschwindigkeit⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| num_leaves | 31 | Maximum number of leaves |
| learning_rate | 0.1 | Boosting learning rate |
Quelle:
qlib/contrib/model/gbdt.pyXGBoost model for stock return prediction.
Geschwindigkeit⚡⚡
Genauigkeit📊📊📊
Quelle:
qlib/contrib/model/xgboost.pyDeep neural network for nonlinear feature extraction and return prediction.
Geschwindigkeit⚡⚡
Genauigkeit📊📊📊
Schlüsselparameter
| hidden_size | 256 | Hidden layer size |
Quelle:
qlib/contrib/model/pytorch_nn.pyAttention-based LSTM for sequential stock data modeling with attention mechanism.
Geschwindigkeit⚡
Genauigkeit📊📊📊
Schlüsselparameter
| hidden_size | 64 | LSTM hidden size |
| num_layers | 2 | Number of LSTM layers |
Quelle:
qlib/contrib/model/pytorch_alstm.pyTemporal Fusion Transformer combining static and temporal features for multi-horizon prediction.
Geschwindigkeit⚡⚡
Genauigkeit📊📊📊
Quelle:
qlib/contrib/model/pytorch_tft.pyTrading-Algorithmen mit maschinellem Lernen, Algorithmus-Referenz
- LightGBMRegressor (Freqtrade)
- Gradient boosting regression model for price movement prediction using LightGBM. Schlüsselparameter: n_estimators (Number of boosting rounds), learning_rate (Step size shrinkage).Quelle: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMRegressor.py.
- LightGBMClassifier (Freqtrade)
- Gradient boosting classification model for directional prediction (up/down/neutral). Schlüsselparameter: n_estimators (Number of boosting rounds).Quelle: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMClassifier.py.
- XGBoostRegressor (Freqtrade)
- XGBoost-based regression model for continuous value prediction. Schlüsselparameter: n_estimators (Number of boosting rounds), max_depth (Maximum tree depth).Quelle: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostRegressor.py.
- XGBoostClassifier (Freqtrade)
- XGBoost-based classification model for directional prediction. Schlüsselparameter: n_estimators (Number of boosting rounds).Quelle: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostClassifier.py.
- CatboostRegressor (Freqtrade)
- CatBoost gradient boosting model with native categorical feature support. Schlüsselparameter: iterations (Number of boosting iterations).Quelle: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/CatboostRegressor.py.
- PyTorchMLPRegressor (Freqtrade)
- Multi-layer perceptron neural network for regression-based price prediction. Schlüsselparameter: hidden_dim (Hidden layer dimension), dropout_percent (Dropout rate).Quelle: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/PyTorchMLPRegressor.py.
- PyTorchTransformerRegressor (Freqtrade)
- Transformer architecture for time-series regression using self-attention mechanism. Schlüsselparameter: num_heads (Number of attention heads), num_layers (Number of transformer layers).Quelle: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/PyTorchTransformerRegressor.py.
- LGBModel (Qlib (Microsoft))
- LightGBM model for stock return prediction using technical and fundamental features. Schlüsselparameter: num_leaves (Maximum number of leaves), learning_rate (Boosting learning rate).Quelle: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/gbdt.py.
- XGBModel (Qlib (Microsoft))
- XGBoost model for stock return prediction. Quelle: 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. Schlüsselparameter: hidden_size (Hidden layer size).Quelle: 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. Schlüsselparameter: hidden_size (LSTM hidden size), num_layers (Number of LSTM layers).Quelle: 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. Quelle: 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. Quelle: https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_gats.py.