A STUDY OF MACHINE LEARNING MODELS FOR CREDIT CARD FRAUD DETECTION

Abstract

Therising concernof creditcardfraudnecessitates the development of effective predictive models to safeguard financial transactions. This paper presents a comprehensive comparison of machine learning models designed to predict credit card fraud. Through an exploratory analysis of a dataset containing transaction details, Support Vector Classifier (SVC), K-Nearest Neighbors (KNN), and Decision Tree models are employed. Hyperparameter tuning is performed to optimize themodels,andtheirperformanceisevaluatedonatestset.The results demonstrate the efficacy of the models in identifying fraudulent transactions, with a particular focus on the tuned SVC model achieving notable accuracy.