Stock Selection Factors from Aggressive Buying Activity

Summary

This study constructs equity selection factors from trade by trade data to measure aggressive buying. It aggregates transactions into minute level buying and selling amounts, then derives buying share and buying intensity measures. The proposed factors can be calculated intraday; the text also describes simpler daily versions for settings where intraday computation is difficult.

After removing the effects of conventional lower frequency factors, some intraday buying share and intensity measures retain monthly stock selection ability. The document reports positive information coefficients, win rates, and long short returns for selected factors. Daily versions also show some ability, but weaker results. The factors correlate with prior stock returns and, in some cases, size, turnover, and volatility, while showing lower correlation with profitability and earnings growth. Performance is described as stronger within the CSI 300 than across the full market. These are reported backtest findings; the text warns that systemic market conditions, liquidity, and policy changes can affect results.

Key ideas

• Minute level trade data can be aggregated into aggressive buying and selling amounts.
• Buying share and buying intensity are used to form stock selection factors.
• Some intraday factors retain monthly predictive ability after orthogonalization against conventional factors.
• Daily versions are easier to calculate but show weaker selection results than intraday measures.
• Factor performance is reported as stronger within the CSI 300, and results may be affected by market, liquidity, and policy risks.

Tags

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