Skip to content
All library documents

Tail-End Intraday Turnover Share as an Equity Alpha Factor

Article BigQuant

Summary

This research note studies whether the timing of stock trading value within the day contains information beyond conventional turnover factors. It examines minute-level turnover distributions, a turnover-share factor over 240 minutes, higher moments, and autocorrelation. The reported analysis finds that much of the signal in the latter measures is explained by traditional turnover factors, while incremental information is concentrated near the market close. It therefore focuses on the share of trading value occurring in the final 20 minutes, called APL20, and combines daily observations into a monthly factor with an exponentially weighted moving average.

After neutralizing common factors, the note reports a negative mean information coefficient of 5.43% in magnitude and a negative RankIC of 5.56% in magnitude, along with a 93% monthly win rate and annualized ICIR of -5.18. For 2014–2019, it reports differentiated returns across ten groups and a long-short portfolio with 23.19% annualized return, 5.90% annualized volatility, 3.94 annualized IR, and 6.38% maximum drawdown. These are historical backtest findings; the note cautions that changing market styles or microstructure may weaken or eliminate the factor.

Key ideas

  • The study tests minute-level trading value patterns as potential equity selection factors.
  • It finds that incremental information beyond traditional turnover measures is concentrated near the close.
  • APL20 measures the share of trading value in the final 20 minutes and is smoothed into a monthly factor.
  • The reported 2014–2019 backtest shows differentiated decile returns and a positive long-short return profile despite negative IC statistics.
  • Historical results may not persist if market styles or trading microstructure change.

Tags

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