Building and Submitting Intraday Factors for the BigQuant Quant Challenge

Summary

This guide explains how to participate in a BigQuant quantitative challenge using A-share minute bars and order-book snapshots to predict future 30-minute VWAP returns. It covers the factor-mining and end-to-end modeling tracks, available templates and data sources, the required `main` entry point, and the output schema for factor submissions. It also describes data handling, leakage safeguards, local evaluation, submission packaging, and the separation between public development and private final evaluation.

For factor research, the guide emphasizes valid sampling times, alignment to the contest stock pool, clean values, and avoiding future data. The platform applies common preprocessing and evaluates information coefficients, long-short performance, stress stability, and turnover. The document is operational guidance rather than a report of a particular factor’s results; it gives no winning method or performance evidence. Its dates, eligibility rules, resource costs, and submission requirements are specific to this contest and may not generalize to other platforms or events.

Key ideas

• The challenge predicts future 30-minute VWAP returns from A-share intraday market data.
• Factor submissions must return date, instrument, and factor values at valid sampling times.
• Researchers must avoid look-ahead data and align outputs with the contest stock universe.
• The evaluation includes information coefficients, long-short Sharpe, stress stability, and turnover.
• Public validation and private final evaluation serve different purposes, and submissions must meet platform packaging requirements.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.