Authors : Sarthak Aggarwal; Vibhuti Nautiyal; Garima Joshi; Nishit Galhotra

Volume/Issue : Volume 8 - 2023, Issue 6 - June

Google Scholar : https://bit.ly/3TmGbDi

Scribd : https://tinyurl.com/mr3uwwn5

DOI : https://doi.org/10.5281/zenodo.8058763

Abstract : It is difficult for credit card firms to detect malicious activities like fraudulent transactions which cause its users to make payments from their accounts without their knowledge for the items that they did not purchase leading them to financial loss. As the world is moving towards digitalization the use of digital money has also increased which has also led to a rise in fraud associated with them parallelly. There are several methods applied to stop fraudulent activities but fraudsters keep on trying to find new ways and methods and always come up with unique ideas to break the security mechanism to commit fraudulent transactions making billions of losses to banks and credit card users globally. Therefore, there is a great demand for a technique for detecting credit card made fraudulent transaction that not only prevents it but also accurately and efficiently anticipates before it happens. This paper uses and explains various techniques for detecting credit card fraud, conducts a thorough analysis of both the existing models and the proposed model, and then conducts a comparison of these techniques based on achieved accuracy, false alarm rate, and detection rate.

Keywords : Random Forest, Logistic Regression, Decision Tree, SVM (Support Vector Mechanism), False Alarm Rate (FAR), Decision Rate.