ABSTRACT We introduce a novel measure of CEO depression by applying machine learning models that analyze vocal acoustic features from CEOs' conference call recordings. Our research was preregistered via the Journal of Accounting Research 's registration‐based editorial process. In this study, we validate this measure and examine associated factors. We find that greater firm risk is positively associated with CEO depression, whereas higher job demands are negatively associated with CEO depression. Female and older CEOs show a lower likelihood of depression. Using this novel measure, we then explore the relationship between CEO depression and career outcomes. Although we do not find any evidence that CEO depression is associated with CEO turnover, we find some evidence that turnover‐performance sensitivity is higher among depressed CEOs. We also find limited evidence of higher compensation and higher pay‐performance sensitivity for depressed CEOs. This study provides new insights into the relationship between CEO mental health and career outcomes.

ABSTRACT We identify sustainability‐focused analysts using recent advances in machine learning combined with conference call transcripts. Sustainability‐focused analysts issue more accurate earnings forecasts, and the stock market reacts more strongly to their revisions. The forecasting advantage of sustainability‐focused analysts is amplified for material sustainability issues, small firms, and growth firms. Consistent with a learning curve in understanding how sustainability issues relate to future performance, we find that less experienced analysts are less likely to focus on sustainability and that they reap fewer benefits in forecast accuracy when they do so. Our results suggest that far from being an inefficient use of time and resources, focusing on sustainability provides a competitive advantage in one of the most pivotal steps in valuation: forecasting earnings.

ABSTRACT We examine how audit partners' geographic proximity to clients affects audit quality. We use hand‐collected data to show that approximately half of audit partners are assigned to clients headquartered more than 100 km away from the partners' home locations. Few of these partners relocate after receiving their assignments and, as a result, more than one‐third of clients are audited by partners who must commute long distances to visit the client in person. We explore this phenomenon by first modeling how distance affects partner‐client matching. We find that partners' geographic proximity to a prospective client is an important matching criterion, but also that trade‐offs are made when other partner characteristics such as industry specialization are more likely to be important. Next, consistent with our prediction, we show that audit quality is lower when partners reside farther from their clients. We corroborate our primary findings by showing that the association between partner distance and audit quality is mitigated when partners have access to direct flights to their clients' headquarters and when clients are geographically dispersed. Our paper should be informative for regulators, practicing auditors, and academics interested in how partner‐client matching affects audit outcomes.