Selecting Directors Using Machine Learning

Abstract

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

Keywords: Corporate Governance, Boards of Directors, Machine Learning

JEL Classification: C10, C45, G30, M12, M51