Social Network Analysis for Fraud Detection

Abstract

Fraud detection is one of the ways to cope with damages associated with fraudulent activities that have become common due to the rapid development of the Internet and electronic business. There is a need to propose methods to detect fraud accurately fast. To achieve accuracy, fraud detection methods are required to consider both kinds of features, features based on the user level and features based on the network level. Therefore, in this paper, a method called MEFUASN is proposed to extract features based on social network analysis. After extracting these features, both the obtained features and the features based on user level are combined together to detect fraud using semi-supervised learning. Evaluation results show that using the proposed feature extraction as a pre-processing step in fraud detection improves the accuracy of detection remarkably, while it controls runtime in comparison with other methods.