A Comparative Study on Credit Card Fraud Detection

Abstract

Credit Card Fraud is increasing rapidly with the development of modern technology. This fraud detection system has been proven essential for banks and financial institution, to minimize their losses. This paper pr- oposes Credit Card Fraud Detection using clustering based on several uns- upervised Machine learning and deep learning algorithms. The method we follow to solve our problem is that we are going to plot the points into two dimensional space and some points turns out to be an outliers and some p- oints forms a valid clusters. These outliers are possible number of cheaters which is nothing but the fraudulent transactions and the bank may reject t- heir credit card application. And valid clusters are not cheaters therefore we are going to allocate them the credit card. So as a result we get the explicit list of customers i.e. the potential cheaters who have cheated. Thus, the clu- stering approach which will give better rating score can be chosen to be one of the best methods to detect fraud. In this paper, we worked with Statlog Australian Credit Card Approval Dataset in which the dependent variables have been removed to maintain the privacy of the customers.