Sustainable Investing and the Cross-Section of Maximum Drawdown

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