How and When Are High-Frequency Stock Returns Predictable?

• 成果类型: Article; Early Access
• 署名作者: Ait-Sahalia, Yacine; Fan, Jianqing; Xue, Lirong; Zhu, Xiaonan
• 署名单位: Princeton University; National Bureau of Economic Research; Princeton University
• 刊物名称: MANAGEMENT SCIENCE
• ISSN/ISSBN: 0025-1909
• DOI: 10.1287/mnsc.2022.02435
• 发表日期: 2025
• 关键词: high-frequency returns; durations; predictability; Machine Learning; random forests; Lasso; Penalized regression

摘要

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.