Alpha Go Everywhere: Machine Learning and International Stock Returns

Darwin Choi; Wenxi Jiang; Chao Zhang

doi:10.1093/rapstu/raaf005

Alpha Go Everywhere: Machine Learning and International Stock Returns

Darwin Choi¹; Wenxi Jiang²; Chao Zhang³

¹ Hong Kong University of Science and Technology , Hong Kong SAR, · ² CUHK Business School, Chinese University of Hong Kong , Hong Kong SAR, · ³ Hong Kong University of Science and Technology (Guangzhou)

The Review of Asset Pricing Studies 2025

Abstract We apply machine learning techniques to predict international stock returns using firm characteristics. Market-specific training is important, as neural network models (NNs) achieve stronger results when they are trained in each market separately than in a global model trained with U.S. data. NNs outperform linear models in predicting stock return rankings and forming profitable portfolios. In contrast, regression trees underperform linear models when the number of observations is low. We also show that adding variables constructed from U.S. firm characteristics, which may contain information beyond the characteristics of international stocks, further enhances the return predictability of market-specific NNs. (JEL C52, G10, G12, G15)

DOI: 10.1093/rapstu/raaf005
Volume: 15 (3-4)
Pages: 288-331
Language: en
Export: BibTeX
Sources: openalex crossref