Quantitative Finance · GitHub

microsoft/qlib

An AI-oriented quant investment platform for machine learning-based research, covering data processing, model training, and backtesting.

82VF score
Maintainer
Microsoft
Market coverage
Global Equity, Quantitative Markets
GitHub stars
46,068
Updated
2026-04-22T07:08:01Z
Best for

Quantitative researchers looking to automate the R&D process and experiment with ML models in finance.

Implementation statusGuide reviewed · 2026-04-22T07:08:01Z
Implementation status

MIT

Expected result

Market dynamics modeling

Known failure mode

High learning curve for non-developers

Compatibility

Global Equity, Quantitative Markets

Why it stands out

  • Market dynamics modeling
  • Reinforcement learning support
  • Automated R&D with RD-Agent

Risks and limitations

  • High learning curve for non-developers
  • Resource intensive for training complex models

Examples and expected outcomes

Example 1

Create a repeatable research memo

  • Sourced evidence
  • Repeatable steps
  • Explicit uncertainty
Example 2

Compare companies with one checklist

  • Sourced evidence
  • Repeatable steps
  • Explicit uncertainty
Example 3

Build a sourced bull/bear review

  • Sourced evidence
  • Repeatable steps
  • Explicit uncertainty

Access requirements

Keys and runtime

Verify current documentation for RD-Agent LLM requirements

License and data rights

MIT

Rate limits

Verify current documentation

Connect to your Agent

Claude config
pip install pyqlib

# Project-scoped Agent Skill layout
.claude/skills/microsoft-qlib-review/SKILL.md
.claude/skills/microsoft-qlib-review/references/

# Restart Claude Code and confirm discovery.
Prompt example

“Use microsoft/qlib to research AAPL. List sources and timestamps first, then separate facts, calculations, risks and missing data. Do not give personalized trading advice.”

When not to use it

  • High learning curve for non-developers
  • Resource intensive for training complex models
Installation

microsoft/qlib

Terminal
pip install pyqlib

Before you install

Review the current license and source code, pin a version, keep credentials out of prompts, and start with read-only permissions.

Project-specific questions

What can microsoft/qlib do in a real workflow?

Market dynamics modeling Reinforcement learning support Automated R&D with RD-Agent

What access and compatibility does microsoft/qlib require?

MIT · Global Equity, Quantitative Markets

What is the main implementation risk with microsoft/qlib?

High learning curve for non-developers Resource intensive for training complex models