Qlib
Microsoft's AI-oriented quant investment platform for building and testing machine-learning alpha models.
GitHub statistics as of 2026-11-10. Status: active = commits in the last 90 days, slowing = in the last year, inactive = older, archived = read-only.
Overview
Qlib covers the whole research loop for machine-learning stock selection: a fast data layer, feature engineering, a model zoo (gradient boosting, LSTM, transformers and more), portfolio construction and backtesting. Its examples are built mostly around Chinese A-share data.
Best for: Researchers building cross-sectional stock-selection models with machine learning.
Strengths
- End-to-end ML research workflow
- Many reference models and benchmarks
- Backed by Microsoft Research, MIT license
Limitations
- Equity factor research, not trading execution
- Default data focuses on China A-shares
- Needs solid ML background
Comparisons
Alternatives in AI and machine learning
All frameworks · Descriptions are our own summary and may lag behind each project's documentation. Check the project's license before using it in a product. Nothing here is investment advice.