Predicting Accounting Misstatements Using Data Mining in Firms Listed in Tehran Stock Exchange

Misstating financial statements are becoming rampant phenomena. An important issue for accounting and auditing is the prediction and detection of misstating in financial statements in Firms Listed in Tehran Stock Exchange in order to help identify in the time interval from 2009 to 2016. We investigate the characteristics of misstating firms on various dimensions, we focus on 23 variables including accrual quality (12 variables), financial performance (4 variables), nonfinancial performance (1 variables), and market-related variables (6 variables). We evaluate features from previous studies of detecting fraudulent intention and material misstatements Out of these companies, 189 (21 companies were misstating and 168 were non-misstating) have been selected as the research sample. The data mining methods employed in this research include Decision Trees (REPTree), Artificial Neural Networks (ANNs) and Bayesian Networks. The obtained results indicated that the Bayesian Networks & Artificial Neural Networks methods had a higher performance and in this regard.