Bank Fraud Detection Using Support Vector Machine

Abstract

With the significant development of communications and computing, bank fraud is growing in its forms and amounts. In this paper, we analyze the various forms of fraud to which are exposed banks d data mining tools allowing its early detection data already accumulated in a bank. We use supervised learning methods Support Vector Machines with Spark (SVM-S) to build models representing normal and abnormal customer behavior and then use it to evaluate validity of new transactions. The results obtained from databases of credit card transactions show that these techniques are effective in the fight against banking fraud in big data. Experiment result from the study show that SVM-S have better prediction performance than Back Propagation Netw orks (BPN). Besides the average prediction, accuracy reaches a maximum when training the data ratio arrives at 0.8.