A Systematic Review of Data Mining Approaches to Credit Card Fraud Detection

Authors: , ,

Abstract: Credit card fraud is a serious and ever-growing problem with billions of dollars lost every year due to fraudulent transactions. Fraud has always been present and will always be. It is also ever changing, as the technology and usage patterns change over time, which makes CCFD (credit card fraud detection) a particularly hard problem. Traditionally, fraud detection relied solely on domain experts’ detection rules, but in the past decade or two, such solutions are being augmented with data mining models for fraud detection. The progress in this area is impeded both by the sensitive nature of the data and great commercial potential – the industrial solutions are understandably kept secret and authentic datasets are rare and few. In this paper we study the CCFD problem with its typical problems and state of the art solution. We survey the recent literature and bring a structured overview of relevant fraud detection features and data mining approaches to this problem.

WSEAS Transactions on Business and Economics, ISSN / E-ISSN: 1109-9526 / 2224-2899, Volume 15, 2018, Art. #43

PDF
XML
Cite
×
Citation Tools
WSEAS AMA
Igor Mekterović, Ljiljana Brkić, Mirta Baranović, "A Systematic Review of Data Mining Approaches to Credit Card Fraud Detection," WSEAS Transactions on Business and Economics, vol. 15, pp. 437-444, 2018, DOI:
Igor Mekterović, Ljiljana Brkić, Mirta Baranović. A Systematic Review of Data Mining Approaches to Credit Card Fraud Detection. WSEAS Transactions on Business and Economics. 2018;15:437-444.
Copy to Clipboard
Citation copied to Clipboard

Certification

---