Financial Statement Fraud Detection: An Analysis of Statistical and Machine Learning Algorithms

Posted: 25 Jan 2013

See all articles by Johan Perols

Johan Perols

University of San Diego - Department of Accountancy; University of San Diego - School of Business Administration

Date Written: March 21, 2010

Abstract

This study compares the performance of six popular statistical and machine learning models in detecting financial statement fraud under different assumptions of misclassification costs and fraud firm to non-fraud firm ratios. The results show, somewhat surprisingly, that logistic regression and support vector machines perform well relative to artificial neural network, bagging, C4.5 and stacking. The results also reveal some diversity in predictors used across the classification algorithms. Out of 42 predictors examined, only 6 are consistently selected and used by different classification algorithms: auditor turnover, total discretionary accruals, Big 4 auditor, accounts receivable, meeting or beating analyst forecasts, and unexpected employee productivity. These findings extend financial statement fraud research and can be used by practitioners and regulators to improve fraud risk models.

Keywords: Analytical auditing, Financial statement fraud, Fraud detection, Fraud predictors, Classification algorithms

Suggested Citation

Perols, Johan, Financial Statement Fraud Detection: An Analysis of Statistical and Machine Learning Algorithms (March 21, 2010). Auditing: A Journal of Practice & Theory, Vol. 30, No. 2, 2011, Available at SSRN: https://ssrn.com/abstract=2206572

Johan Perols (Contact Author)

University of San Diego - Department of Accountancy ( email )

223 Olin Hall
5998 Alcalá Park
San Diego, CA
United States

University of San Diego - School of Business Administration ( email )

5998 Alcala Park
San Diego, CA 92110-2492
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
2,070
PlumX Metrics