Using Machine Learning to Detect Misstatements
Review of Accounting Studies, Forthcoming
53 Pages Posted: 17 Dec 2019 Last revised: 25 Feb 2020
Date Written: December 1, 2019
Machine learning offers empirical methods to sift through accounting data sets with a large number of variables and limited a priori knowledge about functional forms. In this study, we show that these methods help detect and interpret patterns present in ongoing accounting misstatements. We use a wide set of variables from accounting, capital markets, governance, and auditing datasets to detect material misstatements. A primary insight of our analysis is that accounting variables, while they do not detect misstatements well on their own, become most important with suitable interactions with audit and market variables. We also analyze differences between misstatements and irregularities, compare algorithms, examine one-year and twoyear ahead predictions, and interpret groups at greater risk of misstatements.
Keywords: Machine Learning; Big Data; Analytics; Misstatements; AAERs; Accounting Fraud
JEL Classification: C63; D83; G38; K22; K42; M41
Suggested Citation: Suggested Citation