Z. Karimi Zandian - Data Mining Lab, Department of Computer Engineering, Alzahra University, Tehran, Iran
M. R. Keyvanpour - Department of Computer Engineering, Alzahra University, Tehran, Iran

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 and fast. To achieve to accuracy, fraud detection methods need to consider both kind of features, features based on user level and features based on network level. In this paper a method called MEFUASN is proposed to extract features that is based on social network analysis and then both of obtained features and features based on user level are combined together and used to detect fraud using semi-supervised learning. Evaluation results show 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.

Feature extraction, fraud detection, social network analysis, semi-supervised learning, network level features