Real-time Machine Learning in the Cross-Section of Stock Returns

李斌，现为武汉大学经济与管理学院教授、博导、金融系主任，兼任武汉大学教育发展基金会理事兼投资咨询委员会委员、中国金融学年会理事等。研究方向为金融科技、投资管理和人工智能等。他具备金融+科技的跨学科背景与研究能力，在《Journal of Accounting Research》、《Artificial Intelligence》、《Journal of Machine Learning Research》、《管理科学学报》、《世界经济》、《金融研究》、《中国工业经济》、ICML、IJCAI等金融会计和人工智能类期刊会议上发表论文；出版英文专著一部《在线投资组合选择：原理和算法》；主持国家自然科学基金等项目等项目多项，一项自科后评估为“特优”；依托科研成果开发软件系统多套，获得软件著作权多项。

We construct real-time machine learning strategies based on a “universe" of fundamental signals. The out-of-sample performance of these strategies is economically meaningful and statistically significant, but considerably weaker than those documented by prior studies that use curated sets of signals as predictors. Strategies based on a simple recursive ranking of each signal's past performance also yield substantially better out-of-sample performance. We find qualitatively similar results when examining past-return-based signals. Our results suggest that using machine learning methods is beneficial for real-time investors, and that feature engineering is key to significantly enhancing such benefits.