Home / Libraries / ML4T Data / Docs
ML4T Data
ML4T Data Documentation
Unified market data acquisition from 19+ providers
Skip to content

User Guide

Use the User Guide when you are moving from a first fetch to a repeatable workflow with configuration, storage, validation, and updates.

Core Features

  • CLI Reference

    Command-line interface for fetching and managing data.

    CLI Reference

  • Configuration

    YAML configuration for automated data pipelines.

    Configuration

  • Incremental Updates

    Efficient daily updates with gap detection.

    Updates

  • Data Quality

    OHLC validation and anomaly detection.

    Quality

  • Storage

    Hive-partitioned Parquet storage system.

    Storage

Performance

ML4T Data is optimized for speed:

Operation Performance
Sequential fetch (100 symbols) 50-100s
Async batch fetch (100 symbols) 5-15s
Load from storage (100 symbols) 0.165s

Next Steps