StratCraft한국어

오픈소스 라이브러리

Freqtrade

freqtrade/freqtrade★ 28k+

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

언어 Python자산 crypto시장 spot, derivatives유형 framework

지표 기반 템플릿

SampleStrategy

Freqtrade

지표 기반beginner

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

속도⚡⚡

정확도📊📊📊

소스:freqtrade/templates/sample_strategy.py

머신러닝 모델(FreqAI)

머신러닝 기반 가격 예측을 위한 FreqAI 예측 모델. 각 모델은 Freqtrade의 피처 파이프라인을 통한 피처 엔지니어링이 필요합니다.

LightGBMRegressor

Freqtrade

머신러닝intermediate

Gradient boosting regression model for price movement prediction using LightGBM.

속도⚡⚡⚡

정확도📊📊📊

주요 파라미터

n_estimators	1000	Number of boosting rounds
learning_rate	0.01	Step size shrinkage

소스:freqai/prediction_models/LightGBMRegressor.py

LightGBMClassifier

Freqtrade

머신러닝intermediate

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

속도⚡⚡⚡

정확도📊📊📊

주요 파라미터

n_estimators

1000

Number of boosting rounds

소스:freqai/prediction_models/LightGBMClassifier.py

XGBoostRegressor

Freqtrade

머신러닝intermediate

XGBoost-based regression model for continuous value prediction.

속도⚡⚡⚡

정확도📊📊📊

주요 파라미터

n_estimators	1000	Number of boosting rounds
max_depth	6	Maximum tree depth

소스:freqai/prediction_models/XGBoostRegressor.py

XGBoostClassifier

Freqtrade

머신러닝intermediate

XGBoost-based classification model for directional prediction.

속도⚡⚡⚡

정확도📊📊📊

주요 파라미터

n_estimators

1000

Number of boosting rounds

소스:freqai/prediction_models/XGBoostClassifier.py

CatboostRegressor

Freqtrade

머신러닝intermediate

CatBoost gradient boosting model with native categorical feature support.

속도⚡⚡

정확도📊📊📊

주요 파라미터

iterations

1000

Number of boosting iterations

소스:freqai/prediction_models/CatboostRegressor.py

PyTorchMLPRegressor

Freqtrade

머신러닝advanced

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

속도⚡⚡

정확도📊📊📊

주요 파라미터

hidden_dim	128	Hidden layer dimension
dropout_percent	0.2	Dropout rate

소스:freqai/prediction_models/PyTorchMLPRegressor.py

PyTorchTransformerRegressor

Freqtrade

머신러닝advanced

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

속도⚡

정확도📊📊📊📊

주요 파라미터

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

소스:freqai/prediction_models/PyTorchTransformerRegressor.py

강화학습(FreqAI)

Stable Baselines3 위에 구축된 강화학습 에이전트. 에이전트는 레이블된 데이터가 아닌 환경 상호작용을 통해 거래 결정을 학습합니다.

ReinforcementLearner

Freqtrade

강화학습advanced

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

속도⚡⚡

정확도📊📊📊

주요 파라미터

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

소스:freqai/prediction_models/ReinforcementLearner.py

Freqtrade 전략과 FreqAI 모델, 알고리즘 참조

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