Biblioteca de código aberto
Freqtrade
freqtrade/freqtrade★ 28k+
Crypto trading bot framework with FreqAI ML extension supporting multiple machine learning and deep learning models.
Templates baseados em indicadores
Modelos de aprendizado de máquina (FreqAI)
Modelos de previsão FreqAI para previsão de preços baseada em aprendizado de máquina. Cada modelo requer engenharia de features através do pipeline de features do Freqtrade.
Gradient boosting regression model for price movement prediction using LightGBM.
Velocidade⚡⚡⚡
Precisão📊📊📊
Parâmetros principais
| n_estimators | 1000 | Number of boosting rounds |
| learning_rate | 0.01 | Step size shrinkage |
Fonte:
freqai/prediction_models/LightGBMRegressor.pyGradient boosting classification model for directional prediction (up/down/neutral).
Velocidade⚡⚡⚡
Precisão📊📊📊
Parâmetros principais
| n_estimators | 1000 | Number of boosting rounds |
Fonte:
freqai/prediction_models/LightGBMClassifier.pyXGBoost-based regression model for continuous value prediction.
Velocidade⚡⚡⚡
Precisão📊📊📊
Parâmetros principais
| n_estimators | 1000 | Number of boosting rounds |
| max_depth | 6 | Maximum tree depth |
Fonte:
freqai/prediction_models/XGBoostRegressor.pyXGBoost-based classification model for directional prediction.
Velocidade⚡⚡⚡
Precisão📊📊📊
Parâmetros principais
| n_estimators | 1000 | Number of boosting rounds |
Fonte:
freqai/prediction_models/XGBoostClassifier.pyCatBoost gradient boosting model with native categorical feature support.
Velocidade⚡⚡
Precisão📊📊📊
Parâmetros principais
| iterations | 1000 | Number of boosting iterations |
Fonte:
freqai/prediction_models/CatboostRegressor.pyMulti-layer perceptron neural network for regression-based price prediction.
Velocidade⚡⚡
Precisão📊📊📊
Parâmetros principais
| hidden_dim | 128 | Hidden layer dimension |
| dropout_percent | 0.2 | Dropout rate |
Fonte:
freqai/prediction_models/PyTorchMLPRegressor.pyAprendizado por reforço (FreqAI)
Agentes de aprendizado por reforço construídos sobre Stable Baselines3. O agente aprende decisões de trading através da interação com o ambiente em vez de dados rotulados.
Estratégias Freqtrade e modelos FreqAI, referência de algoritmos
- SampleStrategy (Freqtrade)
- Template strategy demonstrating basic technical indicator usage for entry/exit signals. Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqtrade/templates/sample_strategy.py.
- LightGBMRegressor (Freqtrade)
- Gradient boosting regression model for price movement prediction using LightGBM. Parâmetros principais: n_estimators (Number of boosting rounds), learning_rate (Step size shrinkage).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMRegressor.py.
- LightGBMClassifier (Freqtrade)
- Gradient boosting classification model for directional prediction (up/down/neutral). Parâmetros principais: n_estimators (Number of boosting rounds).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMClassifier.py.
- XGBoostRegressor (Freqtrade)
- XGBoost-based regression model for continuous value prediction. Parâmetros principais: n_estimators (Number of boosting rounds), max_depth (Maximum tree depth).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostRegressor.py.
- XGBoostClassifier (Freqtrade)
- XGBoost-based classification model for directional prediction. Parâmetros principais: n_estimators (Number of boosting rounds).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostClassifier.py.
- CatboostRegressor (Freqtrade)
- CatBoost gradient boosting model with native categorical feature support. Parâmetros principais: iterations (Number of boosting iterations).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/CatboostRegressor.py.
- PyTorchMLPRegressor (Freqtrade)
- Multi-layer perceptron neural network for regression-based price prediction. Parâmetros principais: hidden_dim (Hidden layer dimension), dropout_percent (Dropout rate).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/PyTorchMLPRegressor.py.
- PyTorchTransformerRegressor (Freqtrade)
- Transformer architecture for time-series regression using self-attention mechanism. Parâmetros principais: num_heads (Number of attention heads), num_layers (Number of transformer layers).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/PyTorchTransformerRegressor.py.
- ReinforcementLearner (Freqtrade)
- Reinforcement learning agent using Stable Baselines3 (PPO/A2C/etc.) for trading decisions. Parâmetros principais: model_type (RL algorithm (PPO, A2C, etc.)), total_timesteps (Training timesteps).Fonte: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/ReinforcementLearner.py.