Machine Learning vs. Economic Restrictions: Evidence from Stock Return Predictability

• 成果类型: Article
• 署名作者: Avramov, Doron; Cheng, Si; Metzker, Lior
• 署名单位: Reichman University; Syracuse University; Hebrew University of Jerusalem
• 刊物名称: MANAGEMENT SCIENCE
• ISSN/ISSBN: 0025-1909
• DOI: 10.1287/mnsc.2022.4449
• 发表日期: 2023
• 页码: 2587-2619
• 关键词: Machine learning; Return prediction; Neural Networks; Financial distress; FinTech

摘要

This paper shows that investments based on deep learning signals extract profitability from difficult-to-arbitrage stocks and during high limits-to-arbitrage market states. In particular, excluding microcaps, distressed stocks, or episodes of high market volatility considerably attenuates profitability. Machine learning-based performance further deteriorates in the presence of reasonable trading costs because of high turnover and extreme positions in the tangency portfolio implied by the pricing kernel. Despite their opaque nature, machine learning methods successfully identify mispriced stocks consistent with most anomalies. Beyond economic restrictions, deep learning signals are profitable in long positions and recent years and command low downside risk.