How and When Are High-Frequency Stock Returns Predictable?
用机器学习方法研究超高频股票收益和持续时间的可预测性，发现短期可预测性大且普遍，并量化了数据毫秒级时效性对预测的影响。
This paper studies the predictability of ultrahigh-frequency stock returns and durations to relevant price, volume, and transaction events using machine learning methods. We find that contrary to low-frequency and long-horizon returns, where predictability is rare and inconsistent, predictability in high-frequency returns and durations is large, systematic, and pervasive over short horizons. We identify the relevant predictors constructed from trades and quotes data, and we examine what determines the variation in predictability across the stock’s own characteristics and market environments. Next, we compute how the predictability improves with the timeliness of the data on a scale of milliseconds and conversely degrades with delays, providing a valuation of each millisecond gained. Finally, we simulate the impact of getting an (imperfect) peek at the incoming order flow, a look-ahead ability that is often attributed to the fastest high-frequency traders, in terms of improving the predictability of the returns and durations. This paper was accepted by Will Cong, finance. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.02435 .