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 supp

What is 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.

Overview of qlib

What it is

Qlib is an open-source, AI-oriented quantitative investment platform. It aims to use AI technologies to empower quantitative research, from exploring ideas to implementing production systems. The platform supports diverse machine learning modeling paradigms, including supervised learning, market dynamics modeling, and reinforcement learning. It contains the full ML pipeline of data processing, model training, back-testing, and covers the entire quantitative investment chain: alpha seeking, risk modeling, portfolio optimization, and order execution. Qlib is also equipped with RD-Agent, an automated R&D process tool for factor mining and model optimization. The project is hosted on GitHub by Microsoft.

Key features

  • Supports multiple ML paradigms: supervised learning, market dynamics modeling, and reinforcement learning.
  • Covers the full quantitative investment chain: alpha seeking, risk modeling, portfolio optimization, and order execution.
  • Includes RD-Agent for automated factor mining and model optimization in quant R&D.
  • Provides a full ML pipeline: data processing, model training, back-testing, and online serving.
  • Includes a Quant Dataset Zoo and a learning framework for diverse research workflows.
  • Features nested decision framework for optimizing multi-level trading strategies.
  • Supports both offline and online modes with low-cost serving.

Use cases

Qlib is designed for quantitative investment research and production. Use cases include developing and back-testing alpha signals, modeling market dynamics with adaptive techniques, optimizing portfolio allocation, and executing orders. It can be used to train supervised models on heterogeneous financial data, apply reinforcement learning for continuous trading decisions, and leverage RD-Agent for automated factor mining and model optimization. The platform supports building custom quant research workflows and running multiple models in ensemble or nested strategies.

Getting started

To get started, see the repository README for detailed installation instructions, data preparation steps, and workflow examples. Basic quick-start steps include installing Qlib (e.g., via pip or source), preparing data (e.g., downloading and converting Qlib dataset zoo), and running an automated quant research workflow. Commands and examples are provided in the official documentation at https://qlib.readthedocs.io/en/latest.

License and pricing

Qlib is open source under the MIT license. It is free to use, modify, and distribute under the terms of that license. No pricing information is provided for enterprise versions; the project is available for self-hosting and use at no cost.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/microsoftqlib.svg)](https://yunodb.com/tools/microsoftqlib?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/microsoftqlib?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/microsoftqlib.svg" alt="Featured on YunoDB" height="20"></a>