Selecting Directors Using Machine Learning

Abstract Can algorithms assist firms in their decisions on nominating corporate directors? Directors predicted by to perform poorly indeed do compared a realistic pool of candidates out-of-sample tests. Predictably bad directors are more likely be male, accumulate directorships, and have larger networks than the algorithm would recommend place. Companies with weaker governance structures nominate them. Our results suggest that machine learning holds promise for understanding process which chosen has potential help real-world improve governance.