Detecting Fraud Transactions Using Radial Basis Function-Artificial Neural Network

Abstract

nisms are concurrent processes in combating fraud malaise. The hitherto traditional methods of fraud detection are not enough to deal with the present level of sophistry with which financial fraudulent acts are perpetrated. In this work, an architecture that enhances fraud detection using an ensemble radial basis function and artificial neural networks was designed. This research provides a dynamic red flags of previously susceptible transactions that were properly classified to distinguish new cases. This approach is rather proactive than a reactive measures to fraud detection and would found relevance among corporate business professional.