Detecting Credit Card Fraud Using Selected Machine Learning Algorithms

Due to the immense growth of e-commerce and increased online based payment possibilities, credit card fraud has become deeply relevant global issue. Recently, there has been major interest for applying machine learning algorithms as data mining technique for credit card fraud detection. However, number of challenges appear, such as lack of publicly available data sets, highly imbalanced class sizes, variant fraudulent behavior etc. In this paper we compare performance of three machine learning algorithms: Random Forest, Support Vector Machine and Logistic Regression in detecting fraud on real-life data containing credit card transactions. To mitigate imbalanced class sizes, we use SMOTE sampling method. The problem of ever-changing fraud patterns is considered with employing incremental learning of selected ML algorithms in experiments. The performance of the techniques is evaluated based on commonly accepted metric: precision and recall.