Menu

Does daily short volume predict short interest? A three-rank formula, ridge and a tiny transformer on 660,246 windows
📰

Does daily short volume predict short interest? A three-rank formula, ridge and a tiny transformer on 660,246 windows

DEV Community: datascience·Daniel Oliveira·19 days ago
#a4ao6d8E
#devtodatascience#science#devto#dev#short
Reading 0:00
15s threshold

FINRA publishes short volume every day and short interest only twice a month, so people treat the daily "short volume ratio" as a live read on short positions. They aren't the same thing: short volume is a flow of executions (a market maker can sell short to fill a buy order and cover an hour later), short interest is the position still open at settlement. I tested how much the daily flow actually tells you about the next short-interest report, on 660,246 settlement windows across 6,959 stocks from January 2020 to July 2026.

Method 2025 to July 2026 retrospective test, pooled Spearman

Change in the short-volume ratio +0.275

Three-factor rank composite, no fitted coefficients +0.305

Ridge on raw window features +0.343

26,213-parameter numeric transformer, 3-seed ensemble +0.414

The target is the percentage change in reported short interest over the same settlement window. Over the whole 2020 to 2026 panel, the plain ratio change reaches +0.229.

Five findings

1. The signal is real but concurrent.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.