CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING TECHNIQUES

Abstract

Over the previous few decades, the increasing credit card fraud cases has always been a major source of concern. This situation is because of the widespread of new technologies, particularly the growing popularity of online banking transactions. However, to recognize scam tendencies it takes computational strength and complexity in designing and creating the pattern matching rule basis. The major purpose is to identify methods and strategies that have significant influence on fraud detection, with a focus on existing research work. Support Vector Machines (SVMs), naive Bayesian, Artificial Neural Networks (ANNs), Decision Tree, K-Nearest Neighbor (k-NN) and Frequent Pattern Mining algorithms are all studied and compared for detecting suspicious transactions. Ensemble models like bagging and clustering have been utilized in conjunction with an algorithmic technique. Boosting has been performed to a dataset of 284807 transactions that is significantly skewed. To name a few only 492 of the total transactions have been flagged as suspicious. Models of prediction, such asthe logistic as well as XGBoost when used with various resampling approaches have yielded. It has been used to determine a transaction is genuine or fraudulent. The model's performance is assessed using the following criteria: recall, precision, f1-score, precision-recall (PR) curve, and receiver operating characteristics (ROC) curves.