Building and Combining High-Frequency Trading Behavior Factors
Summary
This research summary discusses high-frequency equity factors built from combinations of price and volume data to capture trading behavior. It describes two examples: an illiquidity factor adjusted for price-path changes and a factor based on aggressive buy and sell orders. The summary reports their excess returns, information ratios, long-short returns, and Sharpe ratios for the broad Chinese A-share market, including the illiquidity factor’s results after removing the linear influence of size.
It also considers how these factors relate to established styles and higher-moment factors, and frames their limitations in terms of information overlap, interactions in realized returns, and correlated downside and tail risk. The proposed portfolio approach combines high-frequency factors with equal weights after removing Barra factor exposures. The reported backtest shows improved risk indicators for the composite, but the supplied text omits the full paper, testing period, implementation details, and evidence about transaction costs or out-of-sample robustness.
Key ideas
- Price and volume combinations can produce high-frequency factors with information that is not fully captured by traditional factors.
- The examples use price-path-adjusted illiquidity and aggressive order activity to represent trading behavior.
- The summary reports factor performance measures for the broad A-share market, including results adjusted for size influence.
- High-frequency factors may add information while their returns and downside risks still interact.
- An equal-weight composite, formed after removing Barra exposures, is reported to improve risk indicators in the described backtest.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.