Self-organizing fuzzy and MLP approaches to detecting fraudulent financial reporting
In the fields of accounting and auditing, detection of firms engaged in fraudulent financial reporting has become increasingly important, due to the increased frequency of such events and the attendant costs of litigation. Conventional statistical tools such as logit and probit have not been successful in detecting such firms. In this study, we employ seven redflags which are composed of four financial redflags and three turn over redflags in order to detect targets of the Securities and Exchange Commission's (SEC) investigation of fraudulent financial reporting. Two prominent nonlinear approaches, i.e. neural network and fuzzy sets, are applied to detection of SEC investigation targets and compared with the conventional statistical methods.
IEEE/IAFE Conference on Computational Intelligence for Financial Engineering, Proceedings (CIFEr)
Feroz, Ehsan H. and Kwon, Taek Mu, "Self-organizing fuzzy and MLP approaches to detecting fraudulent financial reporting" (1996). Business Publications. 160.
Source Full-text URL