An Experimental Study with Imbalanced Classification Approaches for Credit Card Fraud Detection

This paper process the detection and prevention of fraudulent activities are critically important to financial institutions. Credit card fraud is a criminal offense. Fraud detection and prevention are costly, time-consuming, and labor-intensive tasks. 

Imbalance classification consists of having a small number of observations of the minority class compared with the majority in the data set. We explored these solutions along with the machine learning algorithms used for fraud detection. We identified their weaknesses and summarized the results that we obtained using a credit card fraud labeled dataset. 

According to this paper, imbalanced classification approaches are ineffective, especially when the data are highly imbalanced and reveals that the existing approaches result in a large number of false alarms, which are costly to financial institutions.