Using Machine Learning to Measure Conservatism

53 Pages Posted: 21 Sep 2021

See all articles by Jeremy Bertomeu

Jeremy Bertomeu

Washington University in St. Louis - John M. Olin Business School

Edwige Cheynel

Washington University in St. Louis - John M. Olin Business School

Yifei Liao

University of California, Irvine - Paul Merage School of Business

Mario Milone

University of California, San Diego (UCSD) - Rady School of Management

Date Written: September 16, 2021

Abstract

Using a neural network, we develop novel measures of conservatism that fits non-linearities and interactions absent in prior literature. The machine-learning measures exhibit (i) fewer economically anomalous observations, (ii) economic associations consistent with existing studies, (iii) less unexplained year-over-year instability, and (iv) higher economic magnitudes consistent with reduced attenuation bias. The measure further reveals intuitive trends toward a secular decline in conservatism in the US. In simulations, linear models perform honorably even in the presence of a complex data-generating process but causal inference based on machine learning is the most robust to misspecification. The approach offers the promise of reducing noise in measurements and design more powerful tests to assess theories of conservatism.

Keywords: machine learning, neural network, accounting, conservatism, measure, proxy

JEL Classification: C1, D2, M4

Suggested Citation

Bertomeu, Jeremy and Cheynel, Edwige and Liao, Yifei and Milone, Mario, Using Machine Learning to Measure Conservatism (September 16, 2021). Available at SSRN: https://ssrn.com/abstract=3924961 or http://dx.doi.org/10.2139/ssrn.3924961

Jeremy Bertomeu (Contact Author)

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

Edwige Cheynel

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

Yifei Liao

University of California, Irvine - Paul Merage School of Business ( email )

Irvine, CA California 92697-3125
United States

Mario Milone

University of California, San Diego (UCSD) - Rady School of Management ( email )

9500 Gilman Drive
Rady School of Management
La Jolla, CA 92093
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
280
Abstract Views
860
rank
153,030
PlumX Metrics