microsoft/qlib

Health v2 · maintenance only

Adoption not part of the score

47960 stars · 7602 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Qlib is an AI-oriented quantitative investment platform from Microsoft that supports the full quant research workflow, from data processing and ML model training to portfolio construction and backtesting. It supports diverse ML paradigms including supervised learning, market dynamics modeling, and reinforcement learning, and integrates with RD-Agent for automated factor mining and model optimization.

Use cases

• backtest quantitative trading strategies on stock data
• train ML models to predict stock returns
• mine alpha factors automatically with LLM agents
• manage and version quant research experiments
• build custom portfolio management strategies
• process and store daily-frequency market data
• research high-frequency trading strategies

When to choose

• you need an end-to-end Python framework for quant research with ML
• you want reproducible backtesting and experiment tracking out of the box
• you want to automate factor mining and model tuning with RD-Agent
• you need support for supervised learning, RL, and market dynamics modeling in one platform

When to avoid

• you need live production trading execution or broker connectivity
• you only need simple charting or portfolio tracking without ML
• you require asset classes beyond equities with first-class support
• you want a no-code point-and-click backtesting tool

Facets

framework · maturity active

machine-learning deep-learning data-science etl benchmarking agent-framework fintech machine-learning data-science large-language-models python windows cross-platform quantitative-finance algorithmic-trading quant backtesting stock-data factor-mining portfolio-management reinforcement-learning investment-research ai-agents linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/qlib")