Cross-Sectional Return Prediction in China’s A-Share Market Based on Lasso and XGBoost: A Comparison with the Fama–MacBeth Multi-Factor Model
In response to the problem of the widespread use of mixed prediction performance metrics in machine learning stock selection literature, the lack of empirical tests on the applicability boundaries of linear and tree-based models under low-dimensional factor settings, and the disconnection of most high-dimensional facto...