Building a Stock Factor from Intraday Relative Volume Entropy

Summary

This research note proposes an equity factor based on how each stock’s intraday volume pattern differs from the market’s. It starts from the common U-shaped market volume profile and argues that a stock with unusually concentrated or uneven trading may have experienced information-driven activity, while a stock following the market pattern may show less distinctive activity. Relative volume is defined by comparing a stock’s volume in each minute with total market volume in that minute.

The described process uses minute-level volume shares, cross-sectional minute averages, and changes in each stock’s relative share to derive an entropy measure. The author interprets lower entropy as potentially signaling information-driven trading and higher entropy as closer market-following behavior; the proposed factor is then transformed by its distance from the cross-sectional mean, with a past-20-day distribution referenced. The note gives no empirical results, complete calculation details, or validation. Its numbered procedure skips steps, so implementation and the claimed predictive meaning need independent clarification and testing.

Key ideas

• The method compares each stock’s minute-by-minute volume with total market volume for the same minute.
• Intraday volume patterns are treated as a possible indicator of unusual information or concentrated trading.
• The proposed entropy factor is adjusted by its absolute distance from the cross-sectional mean.
• The author suggests that very low and very high entropy may each have different trading implications.
• The document provides no backtest and omits steps in its calculation outline.

Tags

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