Skip to content
This page is not translated yet — showing the original. We never ship machine translation as a placeholder.
One commandMIT Tested

Qlib

In one line:Qlib 是一个给量化研究用的开源 AI 平台:从因子挖掘到回测,一套流程跑下来,能。

给量化研究用的开源 AI 平台:从因子挖掘到回测,一套流程跑下来。

Official source

We host and mirror nothing — the official page is the source of truth.

Official icon for Qlib Microsofthttps://github.com/microsoft/qlibOpen official page
Official sourceYou are leaving AIWorksWell for Microsoft. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Install prompt

Copy it, paste it into your AI (Claude Code, Codex, ChatGPT…), and it installs and verifies for you.

48 lines
我需要你帮我在我的机器上安装并运行一个软件。

【软件信息】
名称:Qlib
用途:给量化研究用的开源 AI 平台:从因子挖掘到回测,一套流程跑下来。
官方来源:https://github.com/microsoft/qlib
许可:MIT
Scroll inside the box with your mouse wheel — copying still gives you the full prompt1567 chars

Copy → paste into your own AI → it installs for you

Contact the original author (Microsoft)

Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.

Install failed?

Paste the raw error — once triaged and verified it is written back here, so the next person's AI avoids it. No login needed.

Official visuals

回测结果:分组累计收益曲线
回测结果:分组累计收益曲线 · 官方文档
回测结果:多空收益分布
回测结果:多空收益分布 · 官方文档
官方分析报表:多指标组合视图
官方分析报表:多指标组合视图 · 官方文档

Official images beyond the cover. Click a thumbnail or use the ← → keys to switch. Images are hotlinked from official sources; we never re-host them.

About this entry

它是什么

Qlib 是微软开源(MIT)的面向 AI 的量化研究平台。它把量化研究里最琐碎的那部分——数据组织、因子表达、模型训练、回测评估——做成了一套可复用的流程与工具,让研究者可以把精力放在"想法"本身,而不是反复重搭实验脚手架。它支持从传统机器学习到深度学习的多种建模范式。来源:https://github.com/microsoft/qlibhttps://github.com/microsoft/qlib

怎么用起来

主推「复制提示词」——让 AI 按官方文档帮你建环境、拉数据、跑通第一个例子。人工兜底:建一个干净的 Python 环境 → pip install pyqlib → 按官方 Quick Start 下载示例数据 → 跑一遍内置的基准工作流验证环境。来源:https://github.com/microsoft/qlibhttps://github.com/microsoft/qlib

以上坑来自 https://github.com/microsoft/qlibhttps://github.com/microsoft/qlib 与官方文档。

来源与署名

Mentioned from:https://github.com/microsoft/qlibhttps://github.com/microsoft/qlib · 原作者 Microsoft(MIT)。

Demo videos

Videos are embedded with the platform's own player — the bandwidth is theirs, the playback experience is ours. We never download or re-host. The player loads only if you click, so this page makes no third-party request unless you ask for one.

  • Qlib Scenario Demo (English)

    youtube
    Watch at the sourceyoutubeYou are leaving AIWorksWell for youtube. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.
  • Qlib Demo (中文)

    youtube
    Watch at the sourceyoutubeYou are leaving AIWorksWell for youtube. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.
  • Quant Model Optimization

    youtube
    Watch at the sourceyoutubeYou are leaving AIWorksWell for youtube. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Want higher quality, the full comment stream, or to save it? Use “Watch at the source” — the embedded player's quality is set by the platform, and the source site is the complete experience.

Zero video copies: we store no video files at all.

Summary for AI

Qlib 是微软开源(MIT)的量化研究平台,覆盖从因子挖掘到回测的一整套流程。

A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-06

FAQ

数据从哪来?

历史行情数据需要自行获取,直接跑示例会因缺数据而失败。

回测结果能直接用于实盘吗?

不能。回测与实盘差异巨大(滑点、手续费、流动性),不可直接外推。

Pitfalls / known issues

All recorded from real installs, and injected into the prompt above.

  • •历史行情数据需要自行获取:直接跑示例会因缺数据而失败,先按官方文档准备数据。
  • •Python 与依赖版本较敏感,建议用独立虚拟环境,避免与系统包冲突。
  • •回测收益与实盘差异巨大(滑点、手续费、流动性),任何回测结果都不可直接外推。

You might also like

We store, mirror and repackage nothing. Every install path points to the author’s own official page.

Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.