Design Credit Card Fraud Detection System Using Support Vector Machine, Feature Selection and Cross Validation

In recent years, electronic payments has grown rapidly among internet activities so nowadays has attracted many customers due to its speed, efficiency, cost reduction and ease of access. Credit cards can be considered as one of the most widely used tools for electronic payments transactions . Purpose of this research is the identification and extraction feature of fraudulent transaction followed by correct classification of them into two categories of legal and fraud, using support vector machine algorithm and cross-validation. The results of ths method to show improvement in fraud detection so that false negative reduction has 77%, cost 88% and detection rate increased by 11%.