Authors - P Subhash, P. Abhi Varshini, V. Udai Sree, P. Praneeth Reddy, Sai Mahitha Abstract - The recognition of transaction fraud in credit cards is a major problem that is still faced. It is mainly because of the gap between real and fraud transaction. In traditional methods, evaluations are mainly done with the main eye on accuracy, but it is sometimes inadequate and indecisive because the fraud occurrence is only 1% of all the data. Many studies in this field that have been done lately have focused on deep learning and machine learning structures. A very less number of works really stress on relatively simpler structures that can go well with imbalance and variance in class without the need of any complicated frameworks. A dataset that is publicly accessible has been used here for comparative study and has 284,807 transaction data. For classification, three learning algorithms like Logistic Regression, Random Forest, and XGBoost have been used. Precision-Recall AUC (PR-AUC), Matthews Correlation Coefficient (MCC), precision, and recall have been used to assess the model performance and not just accuracy. Random forest shows a steady outcome with a strong variance between false positive control and detection capability. The analysis also reveals that naive class-weighting strategies can significantly increase recall while producing impractically high false positive rates. Feature importance analysis further enhances interpretability and provides insight into influential transaction components.
Open Zoom