Qlib — AI-Oriented Quantitative Investment Platform

Qlib — AI-Oriented Quantitative Investment Platform

Qlib is Microsoft's end-to-end AI quant investment platform covering the full pipeline from data ingestion to live-order execution. It ships with a rich model zoo (LightGBM, LSTM, Transformer, Temporal Fusion Transformer, and more), a factor-expression engine, a backtesting framework, and portfolio optimization — all designed for reproducible research.

Key Features

• Built-in model zoo: classical ML (LightGBM, XGBoost) + deep learning (LSTM, GRU, TCN, TFT, PatchTST) + RL trading agents
• Hierarchical data layer with point-in-time correctness
• Factor/alpha expression engine for feature engineering
• Portfolio optimization: mean-variance, risk-model-based
• Backtest engine with transaction-cost and slippage modelling
• Integration with real brokers via custom execution backends

Quick Start

pip install pyqlib
python -m qlib.run.get_data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn

import qlib
from qlib.constant import REG_CN
qlib.init(provider_uri="~/.qlib/qlib_data/cn_data", region=REG_CN)
from qlib.contrib.model.gbdt import LGBModel
model = LGBModel()
model.fit(dataset)

npx ai-supply add qlib-ai-quant-platform

Curated mirror of the open-source Qlib (MIT). Get it from the source.