A Light-weight Deep-learning Quant Framework
Report Bug
·
Request Feature
Table of Contents
Homemade light-weight quant framework. Support Sliding windows, hyper-parameter search, backtesting, Reversing Trade and etc. See LSTM stock price prediction demo
自制量化框架。支持滑窗, 超参数搜索, 反向对冲, 回测等。查看基于Quantflow-deep-learning-quant-framework的 LSTM 股票预测 Demo。
- Model
- LSTM
- Seq2seq
- Resnet50-1D
- Prediction
- Signal Classification (Buy, Sell, Hold) 信号分类
- Regression (avg price in next window) 回归
- Backtesting Metrics 回调指标
- Sharpe 夏普
- Maximum Drawdown 最大回撤
- Alpha (regression/annualized) (回归法/年化)
- Beta (regression/annualized) (回归法/年化)
- Interval rate of return 平均区间收益率
- Annualized rate of return (baseline/stretegy) 年化收益率 (基准/策略)
- backtesting rate of return 策略回测收益率
- others
- Reversing Trade Support 反向对冲回调策略
- Sliding Window 滑窗生成器
- focal_loss
- class_weighed_sampling 分类权重采样 (抑制类别不均衡)
- Clone repo.
git clone https://github.com/dr413677671/Quantflow-deep-learning-quant-framework.git
- Install dependencies.
pip install <repo-directory>/requirements.txt
See LSTM stock price prediction demo
Based on these brilliant repos:
- Seq2seq
- LSTM
- Logo genetrared by Stable-Diffusion