Building Daily Stock Factors from Intraday Volume Surges

Summary

The article describes a Chinese-equity factor that looks for unusually large intraday increases in trading amount, then aggregates information around those moments into daily observations. Its rationale is that a volume surge accompanying modest, orderly price movement may indicate broader acceptance of news, while a sharp move could reflect crowded reactions and elevated risk.

The construction flags surges using a threshold based on the mean and standard deviation of intraday amount changes. It measures the following five minute returns and their dispersion, combines these with returns at flagged moments, aggregates by stock and day, then cross-sectionally standardizes and smooths the result. The author argues that using later minutes within the same trading day is feasible if the factor is only computed after that day closes. No performance tests or predictive results are reported. The proposal therefore remains a factor hypothesis, and its usefulness depends on correct time partitioning, data handling, and out-of-sample validation; the article also suggests exploring order book structure as a possible extension.

Key ideas

• The factor identifies intraday volume increases using a threshold derived from the distribution of amount changes.
• It evaluates subsequent minute returns and their variability at flagged moments.
• The intraday measurements are aggregated to daily stock-level features and standardized across stocks.
• The author considers same-day future minute data permissible when the signal is calculated after the trading day ends.
• The article gives a construction rationale but reports no empirical performance evidence.

Tags

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