Measuring CEO Personality Using Machine-Learning Algorithms: A Study of CEO Risk Tolerance and Audit Fees

We rely on recent developments in machine learning and artificial intelligence and use the IBM Watson Personality Insights service to measure personality based on transcripts of Q&A sessions of conference calls made by CEOs. We obtain Big-five personality traits and compute a measure for risk tolerance. We conduct a number of validation tests to show that all personality traits are CEO-specific and not related to firm characteristics and firm performance. We then examine the relation between CEO risk tolerance and audit fees. We find that higher CEO risk tolerance is associated with significantly higher audit fees and that this association is consistent across several Big Five index components. Moreover, we find some evidence that the influence of the CEO’s risk tolerance on audit fees is greater when CEO power is greater. Consistent with upper echelons theory, our results suggest that CEO personalities have an incremental impact on auditors’ assessment of engagement risk.