Evaluating an Abnormal Turnover Factor for Stock Selection

Summary

This note defines abnormal turnover as a comparison between a stock’s recent average turnover and its longer-term average, using a 20-day window against a roughly 250-day window. It reports factor-test statistics and discusses whether the signal may be more useful as a filter than as a standalone ranking rule. The reported information coefficient is 0.03, the information ratio is 0.4151, and the signal exceeds the stated absolute-IC threshold 80.9% of the time. The long portfolio’s annualized return is reported as 19.78%, with a maximum drawdown of 35.01%; long-short turnover is 4.76%. These figures suggest some predictive information alongside meaningful instability and drawdown risk.

The author observes that the IC plot appears positively sloped, while grouped long-short performance does not improve monotonically across factor levels. This raises the possibility of a threshold effect and motivates testing the measure as a screening condition. The note provides no sample period, benchmark, universe details, cost assumptions beyond its turnover comment, or out-of-sample validation. Its reported results therefore do not establish that the factor will generalize or remain profitable.

Key ideas

• Abnormal turnover compares recent average turnover with its longer-term average.
• The reported information coefficient is modest, and the information ratio suggests limited signal stability.
• The long portfolio has a reported annualized return alongside a substantial maximum drawdown.
• Grouped performance appears non-monotonic, so a threshold filter may be worth investigating.
• The note omits sample, benchmark, and validation details needed to assess generalizability.

Tags

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