Measuring Executive Personality Using Machine-Learning Algorithms: A New Approach and Audit Fee-Based Validation Tests

Journal of Business Finance and Accounting, Vol. 47, No. 3-4, pp. 519-544, 2020

Posted: 17 Jan 2018 Last revised: 8 May 2020

See all articles by Karel Hrazdil

Karel Hrazdil

Simon Fraser University

Jiri Novak

Institute of Economic Studies, Faculty of Social Sciences, Charles University in Prague, Czech Republic

Rafael Rogo

University of Cambridge - Judge Business School

Christine I. Wiedman

University of Waterloo

Ray Zhang

Simon Fraser University - Beedie School of Business

Date Written: September 9, 2019

Abstract

We present a novel approach for measuring executive personality traits. Relying on recent developments in machine learning and artificial intelligence, we utilize the IBM Watson Personality Insights service to measure executive personalities based on CEOs’ and CFOs’ responses to questions raised by analysts during conference calls. We obtain the Big Five personality traits – openness, conscientiousness, extraversion, agreeableness and neuroticism – based on which we estimate risk tolerance. To validate these traits, we first demonstrate that our risk-tolerance measure varies with existing inherent and behavioural-based measures (gender, age, sensitivity
of executive compensation to stock return volatility, and executive unexercised-vested options) in predictable ways. Second, we show that variation in firm-year level personality trait measures, including risk tolerance, is largely explained by manager characteristics, as opposed to firm characteristics and firm performance. Finally, we find that executive inherent risk tolerance helps explain the positive relationship between client risk and audit fees documented in the prior literature. Specifically, the effect of CEO risk-tolerance – as an innate personality trait – on audit fees is incremental to the effect of increased risk appetite from equity risk-taking incentives (Vega).
Measuring executive personality using machine-learning algorithms will thus allow researchers to pursue studies that were previously difficult to conduct.

Keywords: Personality, Big Five, Machine Learning, Risk, Audit Fees

JEL Classification: G41, G30, M12, M42

Suggested Citation

Hrazdil, Karel and Novak, Jiri and Rogo, Rafael and Wiedman, Christine I. and Zhang, Ray, Measuring Executive Personality Using Machine-Learning Algorithms: A New Approach and Audit Fee-Based Validation Tests (September 9, 2019). Journal of Business Finance and Accounting, Vol. 47, No. 3-4, pp. 519-544, 2020, Available at SSRN: https://ssrn.com/abstract=3101500 or http://dx.doi.org/10.2139/ssrn.3101500

Karel Hrazdil (Contact Author)

Simon Fraser University ( email )

Faculty of Business Administration
8888 University Drive, Simon Fraser University
Burnaby, British Colombia V5A 1S6
Canada
778-782-6790 (Phone)
778-782-4920 (Fax)

HOME PAGE: http://www.sfubusiness.ca

Jiri Novak

Institute of Economic Studies, Faculty of Social Sciences, Charles University in Prague, Czech Republic ( email )

Opletalova 1606/26
Praha 1, 11000
Czech Republic
+420 222 112 314 (Phone)

HOME PAGE: http://ies.fsv.cuni.cz/cs/staff/novakji

Rafael Rogo

University of Cambridge - Judge Business School ( email )

Trumpington Street
Cambridge, CB2 1AG
United Kingdom

Ray Zhang

Simon Fraser University - Beedie School of Business ( email )

8888 University Drive
Burnaby, British Columbia V5A 1S6
Canada

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
3,380
PlumX Metrics