We use supervised learning to identify factors that predict the cross-section of maximum drawdown for stocks in the US equity market. Our data run from January 1980 to June 2018 and our analysis includes ordinary least squares, penalized linear regressions, tree-based models, and neural networks. We find that the most important predictors tended to be consistent across models, and that non-linear models had better predictive power than linear models. Predictive power was higher in calm periods than stressed periods, and environmental, social, and governance indicators augmented predictive power for non-linear models.
↧