Библиотека с открытым исходным кодом
Freqtrade
freqtrade/freqtrade★ 28k+
Crypto trading bot framework with FreqAI ML extension supporting multiple machine learning and deep learning models.
Шаблоны на основе индикаторов
Модели машинного обучения (FreqAI)
Модели предсказания FreqAI для прогноза цен на основе машинного обучения. Каждая модель требует инженерии признаков через конвейер признаков Freqtrade.
Gradient boosting regression model for price movement prediction using LightGBM.
Скорость⚡⚡⚡
Точность📊📊📊
Ключевые параметры
| n_estimators | 1000 | Number of boosting rounds |
| learning_rate | 0.01 | Step size shrinkage |
Источник:
freqai/prediction_models/LightGBMRegressor.pyGradient boosting classification model for directional prediction (up/down/neutral).
Скорость⚡⚡⚡
Точность📊📊📊
Ключевые параметры
| n_estimators | 1000 | Number of boosting rounds |
Источник:
freqai/prediction_models/LightGBMClassifier.pyXGBoost-based regression model for continuous value prediction.
Скорость⚡⚡⚡
Точность📊📊📊
Ключевые параметры
| n_estimators | 1000 | Number of boosting rounds |
| max_depth | 6 | Maximum tree depth |
Источник:
freqai/prediction_models/XGBoostRegressor.pyXGBoost-based classification model for directional prediction.
Скорость⚡⚡⚡
Точность📊📊📊
Ключевые параметры
| n_estimators | 1000 | Number of boosting rounds |
Источник:
freqai/prediction_models/XGBoostClassifier.pyCatBoost gradient boosting model with native categorical feature support.
Скорость⚡⚡
Точность📊📊📊
Ключевые параметры
| iterations | 1000 | Number of boosting iterations |
Источник:
freqai/prediction_models/CatboostRegressor.pyMulti-layer perceptron neural network for regression-based price prediction.
Скорость⚡⚡
Точность📊📊📊
Ключевые параметры
| hidden_dim | 128 | Hidden layer dimension |
| dropout_percent | 0.2 | Dropout rate |
Источник:
freqai/prediction_models/PyTorchMLPRegressor.pyОбучение с подкреплением (FreqAI)
Агенты обучения с подкреплением на базе Stable Baselines3. Агент учится торговым решениям через взаимодействие со средой, а не на размеченных данных.
Стратегии Freqtrade и модели FreqAI, справочник алгоритмов
- SampleStrategy (Freqtrade)
- Template strategy demonstrating basic technical indicator usage for entry/exit signals. Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqtrade/templates/sample_strategy.py.
- LightGBMRegressor (Freqtrade)
- Gradient boosting regression model for price movement prediction using LightGBM. Ключевые параметры: n_estimators (Number of boosting rounds), learning_rate (Step size shrinkage).Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMRegressor.py.
- LightGBMClassifier (Freqtrade)
- Gradient boosting classification model for directional prediction (up/down/neutral). Ключевые параметры: n_estimators (Number of boosting rounds).Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMClassifier.py.
- XGBoostRegressor (Freqtrade)
- XGBoost-based regression model for continuous value prediction. Ключевые параметры: n_estimators (Number of boosting rounds), max_depth (Maximum tree depth).Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostRegressor.py.
- XGBoostClassifier (Freqtrade)
- XGBoost-based classification model for directional prediction. Ключевые параметры: n_estimators (Number of boosting rounds).Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostClassifier.py.
- CatboostRegressor (Freqtrade)
- CatBoost gradient boosting model with native categorical feature support. Ключевые параметры: iterations (Number of boosting iterations).Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/CatboostRegressor.py.
- PyTorchMLPRegressor (Freqtrade)
- Multi-layer perceptron neural network for regression-based price prediction. Ключевые параметры: hidden_dim (Hidden layer dimension), dropout_percent (Dropout rate).Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/PyTorchMLPRegressor.py.
- PyTorchTransformerRegressor (Freqtrade)
- Transformer architecture for time-series regression using self-attention mechanism. Ключевые параметры: num_heads (Number of attention heads), num_layers (Number of transformer layers).Источник: 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. Ключевые параметры: model_type (RL algorithm (PPO, A2C, etc.)), total_timesteps (Training timesteps).Источник: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/ReinforcementLearner.py.