Classification of SIM box fraud detection using support vector machine and artificial neural network

Abstract

SIM box fraud is classified as one of the dominant types of fraud instead of subscription and superimposed types of fraud. This fraud activity has been increasing dramatically each year due to the new modern technologies and the global superhighways of communication, resulting the decreasing of the revenue and quality of service in telecommunication providers especially in Africa and Asia. This paper outlines the Artificial Neural Network (ANN) and Support Vector Machine (SVM) to detect Global System for Mobile communication (GSM) gateway bypass in SIM Box fraud. The suitable features of data obtained from the extraction process of Customer Database Record (CDR) are used for classification in the development of ANN and SVM models. The performance of ANN is compared with SVM to find which model gives the best performance. From the experiments, it is found that SVM model gives higher accuracy compared to ANN by giving the classification accuracy of 99.06% compared with ANN model, 98.71% accuracy.