An Efficient Framework for Credit Card Fraud Detection using Machine Learning

Credit Card Fraud Detection (CCFD) is a crucial security issue for economic and financial firms nowadays. The way of committing fraud is changing constantly; therefore, it is challenging to predict real-time fraudulent transactions. Thus, we propose an efficient machine learning (ML) based model to test fraud detection using the benchmark dataset. We have tested our proposed model by using the credit card dataset 2023, which contains over 511,767 European credit card transactions from 2023. It securely protects the identification of cardholders and aids in finding potential fraudulent transactions. Different models, such as logistic regression (LR), variants of discriminant, SVM, Naïve Bayes (NB), etc., are used for the performance evaluation of the proposed model based on accuracy, cost, prediction time, and training time. The findings of the study show that the proposed model outperformed other models in terms of accuracy.