Detecting Accounting Fraud in Publicly Traded U.S. Firms Using a Machine Learning Approach

49 Pages Posted: 8 Oct 2015 Last revised: 31 Oct 2019

See all articles by Yang Bao

Yang Bao

Shanghai Jiao Tong University (SJTU) - Antai College of Economics and Management

Bin Ke

National University of Singapore

Bin Li

Wuhan University

Y. Julia Yu

University of Virginia

Jie Zhang

Nanyang Technological University (NTU)

Multiple version iconThere are 2 versions of this paper

Date Written: October 30, 2019

Abstract

We develop a state-of-the-art fraud prediction model using a machine learning approach. We demonstrate the value of combining domain knowledge and machine learning method in model building. We select our model input based on existing accounting theories, but we differ from prior accounting research by using raw accounting numbers rather than financial ratios. We employ one of the most powerful machine learning methods, ensemble learning, rather than the commonly used method of logistic regression. To assess the performance of fraud prediction models, we introduce a new performance evaluation metric commonly used in ranking problems that is more appropriate for the fraud prediction task. Starting with an identical set of theory-motivated raw accounting numbers, we show that our new fraud prediction model outperforms two benchmark models by a large margin: Dechow et al.’s [2011] logistic regression model based on financial ratios and Cecchini et al.’s [2010] support-vector-machine model with a financial kernel that maps raw accounting numbers into a broader set of ratios.

Keywords: fraud prediction, machine learning, ensemble learning

JEL Classification: C53, M41

Suggested Citation

Bao, Yang and Ke, Bin and Li, Bin and Yu, Yingri Julia and Zhang, Jie, Detecting Accounting Fraud in Publicly Traded U.S. Firms Using a Machine Learning Approach (October 30, 2019). Available at SSRN: https://ssrn.com/abstract=2670703 or http://dx.doi.org/10.2139/ssrn.2670703

Yang Bao

Shanghai Jiao Tong University (SJTU) - Antai College of Economics and Management ( email )

No.1954 Huashan Road
Shanghai Jiao Tong University
Shanghai, Shanghai 200030
China

Bin Ke

National University of Singapore ( email )

Mochtar Riady Building, BIZ 1, #07-30
15 Kent Ridge Drive
Singapore, 119245
Singapore
+6566013133 (Phone)

Bin Li

Wuhan University ( email )

Economics and Management School
Wuhan University
Wuhan, Hubei 430072
China

HOME PAGE: http://libinli.com

Yingri Julia Yu (Contact Author)

University of Virginia ( email )

P.O. Box 400173
Charlottesville, VA 22904-4173
United States

Jie Zhang

Nanyang Technological University (NTU) ( email )

S3 B2-A28 Nanyang Avenue
Singapore, 639798
Singapore

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

Paper statistics

Downloads
1,531
Abstract Views
7,294
Rank
22,658
PlumX Metrics