A Survey on Credit Card Fraud Detection and Prevention Using Hybrid Algorithm

Abstract

Fraud related to credit cards is increasing as it becomes the most popular method of payment for both ordinary purchases and those made online. Financial institutions and service providers are facing a significant financial burden as a result of the rising number of electronic payments, which is requiring them to continuously enhance their fraud detection systems. Nonetheless, although being widely used in other fields, contemporary data-driven and learning-based methods are still making moderate progress in business applications. In this paper we are representing the types of credit frauds and its detections by reviewing various published papers and its different methods of solving by various algorithms. This essay contrasts and evaluates a few effective methods for identifying credit card fraud. The approaches used to detect credit card fraud are the Dempster Shafer and Bayesian Learning Fusion, Hidden Markov Model, Artificial Neural Networks and Bayesian Learning Approach BLAST and SSAHA Hybridization, and Fuzzy Darwinian System.[1] A description of these methods is provided in Section II. Part III provides a comparison of such strategies, and Section IV provides a summary of fraud detection methods.