Skip to content
All library documents

Intraday Volume-Tide Factors for Stock Selection

Article BigQuant

Summary

This study proposes a stock-selection factor derived from intraday volume patterns. It defines a daily volume “tide” by smoothing minute-level volume with a nine-minute neighborhood, locating its peak, and identifying low-volume points before and after that peak. The price change per minute between those points becomes a daily measure, averaged over recent sessions. The process is also split into stronger and weaker halves based on the relative endpoint volumes; the final factor equally combines the stronger-half measure with a stability measure for the weaker half.

The report describes monthly long-short backtests on Chinese equities, including tests after industry and style-factor adjustment and across broad index universes. It reports favorable historical results, while also noting correlations with volatility and turnover. The evidence is retrospective and tied to the stated sample and methodology; the report warns that historical relationships may fail or vary by market conditions. The summary does not establish live performance or account for implementation costs.

Key ideas

  • A daily volume tide is defined using smoothed intraday volume, its peak, and low-volume points on either side.
  • The rate of price change across the full tide is averaged over recent sessions to form a factor.
  • The tide is divided into stronger and weaker halves, with the final factor combining stronger-half behavior and weaker-half stability.
  • The report evaluates the factor with monthly stock-selection backtests and adjusts for industry and style exposures.
  • The factor’s reported results are historical and may not persist across market conditions.

Tags

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