StratCraftItaliano

Libreria open source

Freqtrade

freqtrade/freqtrade★ 28k+

Crypto trading bot framework with FreqAI ML extension supporting multiple machine learning and deep learning models.

Linguaggio PythonAsset cryptoMercati spot, derivativesTipo framework

Template basati su indicatori

SampleStrategy

Freqtrade

Basato su indicatoribeginner

Template strategy demonstrating basic technical indicator usage for entry/exit signals.

Velocità⚡⚡

Accuratezza📊📊📊

Sorgente:freqtrade/templates/sample_strategy.py

Modelli di machine learning (FreqAI)

Modelli di previsione FreqAI per la previsione dei prezzi basata sul machine learning. Ogni modello richiede feature engineering tramite la pipeline di feature di Freqtrade.

LightGBMRegressor

Freqtrade

Machine Learningintermediate

Gradient boosting regression model for price movement prediction using LightGBM.

Velocità⚡⚡⚡

Accuratezza📊📊📊

Parametri chiave

n_estimators	1000	Number of boosting rounds
learning_rate	0.01	Step size shrinkage

Sorgente:freqai/prediction_models/LightGBMRegressor.py

LightGBMClassifier

Freqtrade

Machine Learningintermediate

Gradient boosting classification model for directional prediction (up/down/neutral).

Velocità⚡⚡⚡

Accuratezza📊📊📊

Parametri chiave

n_estimators

1000

Number of boosting rounds

Sorgente:freqai/prediction_models/LightGBMClassifier.py

XGBoostRegressor

Freqtrade

Machine Learningintermediate

XGBoost-based regression model for continuous value prediction.

Velocità⚡⚡⚡

Accuratezza📊📊📊

Parametri chiave

n_estimators	1000	Number of boosting rounds
max_depth	6	Maximum tree depth

Sorgente:freqai/prediction_models/XGBoostRegressor.py

XGBoostClassifier

Freqtrade

Machine Learningintermediate

XGBoost-based classification model for directional prediction.

Velocità⚡⚡⚡

Accuratezza📊📊📊

Parametri chiave

n_estimators

1000

Number of boosting rounds

Sorgente:freqai/prediction_models/XGBoostClassifier.py

CatboostRegressor

Freqtrade

Machine Learningintermediate

CatBoost gradient boosting model with native categorical feature support.

Velocità⚡⚡

Accuratezza📊📊📊

Parametri chiave

iterations

1000

Number of boosting iterations

Sorgente:freqai/prediction_models/CatboostRegressor.py

PyTorchMLPRegressor

Freqtrade

Machine Learningadvanced

Multi-layer perceptron neural network for regression-based price prediction.

Velocità⚡⚡

Accuratezza📊📊📊

Parametri chiave

hidden_dim	128	Hidden layer dimension
dropout_percent	0.2	Dropout rate

Sorgente:freqai/prediction_models/PyTorchMLPRegressor.py

PyTorchTransformerRegressor

Freqtrade

Machine Learningadvanced

Transformer architecture for time-series regression using self-attention mechanism.

Velocità⚡

Accuratezza📊📊📊📊

Parametri chiave

num_heads	8	Number of attention heads
num_layers	2	Number of transformer layers

Sorgente:freqai/prediction_models/PyTorchTransformerRegressor.py

Apprendimento per rinforzo (FreqAI)

Agenti di apprendimento per rinforzo costruiti su Stable Baselines3. L'agente apprende decisioni di trading tramite l'interazione con l'ambiente anziché dati etichettati.

ReinforcementLearner

Freqtrade

Apprendimento per rinforzoadvanced

Reinforcement learning agent using Stable Baselines3 (PPO/A2C/etc.) for trading decisions.

Velocità⚡⚡

Accuratezza📊📊📊

Parametri chiave

model_type	PPO	RL algorithm (PPO, A2C, etc.)
total_timesteps	10000	Training timesteps

Sorgente:freqai/prediction_models/ReinforcementLearner.py

Strategie Freqtrade e modelli FreqAI, riferimento algoritmi

SampleStrategy (Freqtrade): Template strategy demonstrating basic technical indicator usage for entry/exit signals. Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqtrade/templates/sample_strategy.py.
LightGBMRegressor (Freqtrade): Gradient boosting regression model for price movement prediction using LightGBM. Parametri chiave: n_estimators (Number of boosting rounds), learning_rate (Step size shrinkage).Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMRegressor.py.
LightGBMClassifier (Freqtrade): Gradient boosting classification model for directional prediction (up/down/neutral). Parametri chiave: n_estimators (Number of boosting rounds).Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/LightGBMClassifier.py.
XGBoostRegressor (Freqtrade): XGBoost-based regression model for continuous value prediction. Parametri chiave: n_estimators (Number of boosting rounds), max_depth (Maximum tree depth).Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostRegressor.py.
XGBoostClassifier (Freqtrade): XGBoost-based classification model for directional prediction. Parametri chiave: n_estimators (Number of boosting rounds).Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/XGBoostClassifier.py.
CatboostRegressor (Freqtrade): CatBoost gradient boosting model with native categorical feature support. Parametri chiave: iterations (Number of boosting iterations).Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/CatboostRegressor.py.
PyTorchMLPRegressor (Freqtrade): Multi-layer perceptron neural network for regression-based price prediction. Parametri chiave: hidden_dim (Hidden layer dimension), dropout_percent (Dropout rate).Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/PyTorchMLPRegressor.py.
PyTorchTransformerRegressor (Freqtrade): Transformer architecture for time-series regression using self-attention mechanism. Parametri chiave: num_heads (Number of attention heads), num_layers (Number of transformer layers).Sorgente: 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. Parametri chiave: model_type (RL algorithm (PPO, A2C, etc.)), total_timesteps (Training timesteps).Sorgente: https://github.com/freqtrade/freqtrade/blob/develop/freqai/prediction_models/ReinforcementLearner.py.