# 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 modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

Repository: https://github.com/microsoft/qlib
Canonical: https://ross.abutalabs.com/products/qlib
Homepage: https://qlib.readthedocs.io/en/latest/
Language: Python
License: MIT
License Family: permissive
Topics: quantitative-finance, machine-learning, stock-data, platform, finance, algorithmic-trading, python, investment, quant, quantitative-trading, quant-dataset, quant-models, auto-quant, fintech, research-paper, paper, research, deep-learning
Last push: 2026-07-23T08:15:29+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 11, longevity 100
- inputs: {"age_days": 2210, "days_push": 41, "days_rel": 383, "gap_med": 235, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 47960, forks 7602 (observed 2026-08-28T04:12:11.371553+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: machine-learning, deep-learning, data-science, etl, benchmarking, agent-framework
- domain: fintech, machine-learning, data-science, large-language-models
- platform: python, windows, cross-platform
- tags: quantitative-finance, algorithmic-trading, quant, backtesting, stock-data, factor-mining, portfolio-management, reinforcement-learning, investment-research, ai-agents, linux, macos

## Member repositories
- microsoft/qlib (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.371553+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:20:45.936160+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/qlib (fetched 2026-08-28T04:12:11.371553+00:00, sha 418712669441)
  - homepage: https://qlib.readthedocs.io/en/latest/ (fetched 2026-08-29T07:42:10.032666+00:00, sha 79acaf8cbf44)
- Data as of 2026-08-30T08:39:29.467469+00:00.