Credit Card Fraud Detection Using Machine Learning Techniques

• Published in: 2023 First International Conference on Advances in Electrical, Electronics and Computational Intelligence (ICAEECI) pp. 1 - 8
• Main Authors: Murkute, Purvi, Dhule, Chetan, Lipte, Praneti, Agrawal, Rahul, Chavhan, Nekita
• Format: Conference Proceeding
• Language: English
• Published: IEEE 19-10-2023
• Subjects: Adaptation models; Area Under Precision Recall Curve (AUPRC); Area Under the Receiver Operating Characteristic (AUC-ROC); Boosting; Credit Card Fraud Detection; Credit cards; Gradient Boosting Machines; Logistic regression; Machine learning algorithms; Measurement; Random Forest; Receivers; XGBoost
• DOI: 10.1109/ICAEECI58247.2023.10370832

Due to the advancement of online transactions also widespread usage of credit cards for electronic payments, credit card fraud had major concerns in the financial sectors. Efficient and effective fraud detection techniques are urgently needed to protect financial institutions and consumers against evolving and sophisticated fraudulent activity. This study analyse the methods and developments used to find credit card frauds. With the objective to detect credit card fraud using an extremely unbalanced dataset, this research gives a thorough evaluation of 4 widely known machine learning algorithms: Logistic Regression, Random Forest, Gradient Boosting Machines (GBM), and XGBoost. To assess how well the algorithms detect fraudulent transactions, the area under the precision-recall curve (AUPRC) and Area Under the Receiver Operating Characteristic (AUC-ROC) was estimated.