Sustainable Investing and the Cross-Section of Maximum Drawdown

Abstract

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 1973 to December 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. Environmental, social, and governance indicators did not impact the predictive power for non-linear models, despite their negative correlation with maximum drawdown.