Predicting Bankruptcy After The Sarbanes-Oxley Act Using The Most Current Data Mining Approaches

Abstract

Our study proposes several current data mining methods to predict bankruptcy after the Sarbanes-Oxley Act (2002) using 2007-2008 U.S. data. The Sarbanes-Oxley Act (SOX) of 2002 was introduced to improve the quality of financial reporting and minimize corporate fraud in the U.S. Because of this SOX implementation, a company’s financial statements are assumed to provide higher quality financial information for investors and other stakeholders. The results of our data mining approaches in our bankruptcy prediction study show that Bayesian Net method performs the best (85% overall prediction rate with 94% in AUC), followed by J48 (85% with 82% AUC), Decision Table (83.52%), and Decision Tree (82%) methods using financial and other data from the 10-K report and Compustat. These results are better than previous bankruptcy prediction studies before the SOX implementation using most current data mining approaches.