Using Benford’s Law on Minute Volumes to Classify Stocks for Factor Analysis

Summary

The report proposes using Benford’s law, the uneven distribution of leading digits found in many datasets, to study stock minute-volume data. From those statistics, it constructs an “institutional footprint” measure: higher values are interpreted as stronger traces of institutional activity. The intended use is to segment stocks when evaluating stock-selection factors.

Its central distinction is between factor timing, which asks when a factor works over time, and scenario analysis, which asks for which stocks a factor works across the cross-section. The proposed measure is presented as a possible way to support the latter. The supplied text gives the rationale and research framing but not the full report, indicator formula, sample construction, validation results, or implementation details. It therefore does not establish that the measure reliably identifies institutional trading or improves factor selection. The authors also caution that the tests use historical data and may not generalize to future markets.

Key ideas

• Benford’s law describes how leading digits are distributed unevenly in many datasets.
• The report applies this idea to stock minute-volume statistics to create an institutional-activity proxy.
• Higher values of the proposed measure are interpreted as stronger institutional traces.
• The measure is framed as a way to assess which stocks suit a factor, complementing time-based factor timing.
• The available summary omits the formula and empirical validation details, and historical results may not persist.

Tags

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