One-class support vector machines approach to anomaly detection

Abstract

This article presents two-class and one-class support vector machines (SVM) for detection of fraudulent credit card transactions. One-class SVM classification with different kernels is considered for a dataset of fraudulent credit card transactions treating the fraud transactions as outliers. The effectiveness of the two-class C-Support Vector Classification (C-SVC) and ν-Support Vector Machines with different kernels are also presented on a fraudulent credit card transactions dataset. We describe and compare the performance of binary classifiers using balanced and imbalanced datasets with one-class SVM classifiers. The results of these methods are demonstrated on a credit card fraud dataset to show the superiority of one-class SVM for the anomaly detection problem. © 2013 Copyright Taylor and Francis Group, LLC.