An Improved CCF Detector to Handle the Problem of Class Imbalance with Outlier Normalization Using IQR Method

E-commerce has increased online credit card usage nowadays. Similarly, credit card transactions have increased for physical sales and purchases. This has increased the risk of credit card fraud (CCF) and made payment networks more vulnerable. Therefore, there is a need to develop a precise CCF detector to control such online fraud. Previously, many studies have been presented on CCF detection and gave good results and performance. However, these solutions still lack performance, and most of them have ignored the outlier problem before applying feature selection and oversampling techniques to give solutions for classification. The class imbalance problem is most prominent in available datasets of credit card transactions. Therefore, the proposed study applies preprocessing to clean the feature set at first. Then, outliers are detected and normalized using the IQR method. This outlier normalizes data fed to the Shapiro method for feature ranking and the 20 most prominent features are selected. This selected feature set is then fed to the SMOTEN oversampling method, which increases the minority class instances and equalizes the positive and negative instances. Next, this cleaned feature set is then fed to five ML classifiers, and four different splits of holdout validation are applied. There are two experiments conducted in which, firstly, the original data are fed to five ML classifiers and the holdout validation technique is used, in which the AUC reaches a maximum of 0.971. In Experiment 2, outliers are normalized, features are selected using the Shapiro method, and oversampling is performed using the SMOTEN method. This normalized and processed feature set is fed to five ML classifiers via holdout validation methods. The experimental results show a 1.00 AUC compared with state-of-the-art studies, which proves that the proposed study achieves better results using this specific framework.