GitHub - microsoft/qlib: Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML
a month ago
- #machine learning
- #AI
- #quantitative investment
- RD-Agent��� released, supporting automated factor mining and model optimization in quant investment R&D.
- RD-Agent is available on GitHub with demo videos in English and Chinese.
- Several demo videos provided for different scenarios: Quant Factor Mining, Quant Factor Mining from reports, Quant Model Optimization.
- Paper and code for R&D-Agent-Quant framework published.
- List of features and their release status, including R&D-Agent-Quant, BPQP, LLM-driven Auto Quant Factory, KRNN and Sandwich models, Qlib v0.9.0, RL Learning Framework, HIST and IGMTF models, and more.
- Qlib is an open-source, AI-oriented quantitative investment platform supporting diverse machine learning modeling paradigms.
- Qlib supports the full ML pipeline from data processing to model training and back-testing, covering alpha seeking, risk modeling, portfolio optimization, and order execution.
- Detailed instructions for installing Qlib via pip or from source, including dependencies and troubleshooting tips.
- Data preparation steps, including downloading and updating datasets, and checking data health.
- Docker setup for Qlib, including pulling the image, running the container, and executing scripts.
- Qrun tool for automating quant research workflows, including model training, backtesting, and evaluation.
- Graphical reports analysis and modularized interface for customized quant research workflows.
- List of models supported by Qlib, including GBDT, MLP, LSTM, GRU, ALSTM, GATs, SFM, TFT, TabNet, and more.
- Performance comparison of different data storage solutions, highlighting Qlib's efficiency.
- Community contributions and development guidelines, including how to submit pull requests and become a maintainer.