A Response to “Critique of an Article on Machine Learning in the Detection of Accounting Fraud”

by Yang Bao, Bin Ke, Bin Li, Y. Julia Yu, and Jie Zhang

Read this article

Read Now PDF

Access statistics: 4,515 article downloads; 2,641 complete issue downloads; Total: 7,156

Yang Bao is an assistant professor at Shanghai Jiao Tong University. His email address is baoyang@sjtu.edu.cn.

Bin Ke is a professor at National University of Singapore. His email address is bizk@nus.edu.sg.

Bin Li is a professor at Wuhan University. His email address is binli.whu@whu.edu.cn.

Y. Julia Yu is an assistant professor at University of Virginia. Her email address is julia.yu@virginia.edu.

Jie Zhang is an associate professor at Nanyang Technological University. His email address is zhangj@ntu.edu.sg.

Abstract

Stephen Walker (2021) raises two empirical issues about our article in the Journal of Accounting Research (Bao, Ke, Li, Yu, and Zhang 2020). The first one is about our treatment of missing values for the raw financial statement variables. The second one is about our treatment of serial fraud. Walker (2021) suggests an alternative approach to dealing with serial fraud and claims that inferences change significantly if his approach is adopted. We reexamine the impact of the two issues on our inferences and find no evidence that these two issues alter our paper’s inferences.

This article is a response to Critique of an Article on Machine Learning in the Detection of Accounting Fraud by Stephen Walker (EJW, March 2021).

Response to this article by Stephen Walker: Rejoinder to the Critique of an Article on Machine Learning in the Detection of Accounting Fraud (EJW, September 2021).