We examine return predictability with machine learning in 46 international stock markets. We calculate 148 stock characteristics and use them to feed a repertoire of different models. The algorithms extract predictability mainly from simple, yet popular, factor types—such as momentum,...

Does factor momentum drive the stock price momentum? Inspired by the recent findings from the United States, we revisit this relationship across 51 markets. The factor momentum effect remains strong—both within and across countries—regardless of typical drivers of return predictability....

Does factor momentum drive the stock price momentum? Motivated by the recent findings from the United States, we revisit this relationship across 51 countries. The evidence on factor momentum's ability to capture the stock momentum profits depends fundamentally on methodological and dataset...

We compare the performance of the linear regression model, which is the current standard in science and practice for cross-sectional stock return forecasting, with that of machine learning methods, i.e., penalized linear models, support vector regression, random forests, gradient boosted trees...