Short Selling Activity and Future Returns: Evidence from FinTech Data

We use a novel dataset from a leading FinTech company (S3 Partners) to study the ability of short interest to predict the cross-section of U.S. stock returns. We find that short interest (i.e. the quantity of shares shorted expressed as the fraction of shares outstanding) is a bearish indicator, consistent with theoretical predictions and with the intuition that short sellers are informed traders. The hedged portfolio long (short) in the top (bottom) short-interest decile generates an annual 4-Factor Fama-French alfa of -7.6% when weighting stocks equally and of -6.24% when weighting stocks based on market capitalization. Conditioning on past returns improves the predictive accuracy of short interest: the hedged short-interest portfolio that only uses stocks that appreciated the most in the past six months generates an alfa of -17.88%. Multivariate regressions that control for other known drivers of stock returns (e.g. size, value and liquidity) confirm the validity of these findings. In both Fama-MacBeth and Panel regressions we find that a one standard deviation increase in short interest predicts a drop in future adjusted returns of between 4.3% and 9.3%.