microsoft/qlib

Project overview

Qlib is a modular framework for applying AI and machine learning to quantitative investment research. It supports building complete workflows from data collection through model training and backtesting, with configurable components that can be used independently or orchestrated together.

Project type

Workflow · Model Runtime · Data Processing

Use cases

Data Analysis

Deployment

Refer to project documentation

License

MIT

Best for

• Researchers, data teams, and AI engineers who need a modular framework to build, train, and backtest machine learning models for quantitative investment.
• Teams that want to assemble standalone components into a custom quant workflow or use a CLI runner for end-to-end automation.

Key capabilities

• The qrun tool executes the entire workflow automatically, covering dataset construction, model training, backtesting, and evaluation based on a YAML configuration file.
• Supports reinforcement learning to model continuous investment decisions and optimize trading strategies through interaction with the environment.

Limitations and risks

• The run_all_model.py script currently supports only Linux.
• The TFT model supports only Python 3.6 through 3.7 due to a dependency on tensorflow version 1.15.0.
• Changes in pandas groupby behavior can cause errors in specific reinforcement learning and benchmark scripts.
• Data collected from Yahoo Finance may not be accurate enough for all use cases; users with high-quality datasets should prepare and supply their own data.
• The official dataset is temporarily unavailable due to stricter data security policies, requiring users to source and prepare data independently.

Getting started

• Installation difficulty is moderate because it requires managing Python environments and downloading market data separately. The path to first success is to install via pip, download data using provided scripts, initialize Qlib with the data path, and execute qrun on a configuration file.

Evidence and sources

• GitHub project description: Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions.
• README: Qlib provides a strong infrastructure to support Quant research.
• README: Qlib provides a tool named `qrun` to run the whole workflow automatically (including building dataset, training models, backtest and evaluation).
• README: Qlib also provides a modularized interface to allow researchers to build their own workflow by code.
• README: Here is a list of models built on `Qlib`.

Reviewed at: 2026-07-17T07:06:42Z