How quantmlresearch/qlib works
Qlib is an AI-oriented quantitative investment platform. A researcher’s documented workflow moves from market data through data processing and model training to backtesting and analysis; the platform also covers alpha research, risk modeling, portfolio optimization, reinforcement learning, and online model updates. The graph combines those documented capabilities with relationships visible in the supplied source index and excerpts. Several capability paths are directory-level because their implementation files were not sampled.
Main entry points: handler.py Dataset Handler · trainer.py Model Trainer · data.py Market Data · executor.py Trade Executor
Components 22
Market Data
- Market Data
qlib/data/data.py - Data Cache
qlib/data/cache.py - Dataset Handler
qlib/data/dataset/handler.py - Data Processors
qlib/data/dataset/processor.py - Data Handlers
qlib/contrib/data
Research and Modeling
- ML Models
qlib/contrib/model - Model Trainer
qlib/model/trainer.py - Alpha Evaluation
qlib/contrib/evaluate.py - Risk Models
qlib/model/riskmodel/base.py - Portfolio Optimizers
qlib/contrib/strategy/optimizer - RL Framework
qlib/rl/trainer/trainer.py
Trading Simulation
- Trading Strategy
qlib/strategy/base.py - Trade Decisions
qlib/backtest/decision.py - Trade Executor
qlib/backtest/executor.py - Simulated Exchange
qlib/backtest/exchange.py - Account and Positions
qlib/backtest/account.py - Backtest Reports
qlib/backtest/report.py
Workflow and Serving
- Initialization
qlib/__init__.py - Experiment Workflow
qlib/workflow/recorder.py - Online Updates
qlib/workflow/online/manager.py - Online Strategies
qlib/workflow/online/strategy.py
Other components
- Quant Researcher
Connections 23
- Quant Researcher → Market Data: explores data
README.md - Quant Researcher → Experiment Workflow: runs research
README.md - Initialization → Data Cache: initializes cache
qlib/__init__.py - Market Data → Data Cache: uses cache
qlib/data/data.py - Dataset Handler → Data Processors: uses processors
qlib/data/dataset/handler.py - Market Data → Dataset Handler: feeds processing
README.md - Dataset Handler → Model Trainer: supplies training data
qlib/model/trainer.py - Model Trainer → ML Models: trains models
README.md - ML Models → Alpha Evaluation: produces signals
README.md - Alpha Evaluation → Risk Models: informs investment research
README.md - Risk Models → Portfolio Optimizers: supports allocation
README.md - Portfolio Optimizers → Trading Strategy: guides strategy
README.md - Trading Strategy → Trade Decisions: makes decisions
qlib/backtest/decision.py - Trade Decisions → Trade Executor: directs execution
qlib/backtest/executor.py - Trade Executor → Simulated Exchange: executes trades
qlib/backtest/executor.py - Trade Executor → Account and Positions: updates account
qlib/backtest/executor.py - Account and Positions → Backtest Reports: provides results
README.md - Model Trainer → Experiment Workflow: records experiments
qlib/model/trainer.py - Online Updates → Online Strategies: manages strategies
qlib/workflow/online/manager.py - Online Updates → Model Trainer: re-trains models
qlib/workflow/online/manager.py - Quant Researcher → RL Framework: trains policies
README.md - RL Framework → Trading Strategy: supports trading
README.md - Data Handlers → Dataset Handler: extends handlers
qlib/contrib/data/handler.py