Using machine learning to detect misstatements

• 成果类型: Article
• 署名作者: Bertomeu, Jeremy; Cheynel, Edwige; Floyd, Eric; Pan, Wenqiang
• 署名单位: Washington University (WUSTL); University of California System; University of California San Diego; Columbia University
• 刊物名称: REVIEW OF ACCOUNTING STUDIES
• ISSN/ISSBN: 1380-6653
• DOI: 10.1007/s11142-020-09563-8
• 发表日期: 2021
• 页码: 468-519
• 关键词: earnings; FRAUD; audit; QUALITY; fees

摘要

Machine learning offers empirical methods to sift through accounting datasets with a large number of variables and limiteda prioriknowledge 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 important with suitable interactions with audit and market variables. We also analyze differences between misstatements and irregularities, compare algorithms, examine one-year- and two-year-ahead predictions and interpret groups at greater risk of misstatements.