Detection of fraud risks in retailing sector using MLP and SVM techniques

Abstract

In today’s business conditions, where business activities are spreading over a wide geographical area, fraudauditing processes have crucial importance especially for the retailing sector which has a high branch network. In theretailing sector, especially purchasing processes are subject to high fraud risks. This paper shows that it is possibleto detect fraudulent processes by applying data mining techniques on operational data related to purchasing activities.Within this scope, in order to detect the fraudulent purchasing operations, support vector machine (SVM) models withdifferent kernels and artificial neural networks methods have been used and successful results have been achieved. Theresults of the two methods have been examined comparatively and it shows that optimized SVM classifier outperformsothers. Besides, in this study, it is presumed that the detected fraud data can be proactively used in the struggle againstfraud with fraud-governance risk and compliance software by converting it into scenario analysis.