Automating fraud prevention in credit and debit transactions through intelligent queue systems and regression testing
1 Wells Fargo, Charlotte, North Carolina, USA.
2 The Vanguard Group, Charlotte, North Carolina, USA.
3 Independent Researcher, Sheffield, UK.
4 Independent Researcher, United Kingdom.
Review
International Journal of Frontiers in Engineering and Technology Research, 2024, 07(02), 044–056.
Article DOI: 10.53294/ijfetr.2024.7.2.0048
Publication history:
Received on 06 October 2024; revised on 14 November 2024; accepted on 17 November 2024
Abstract:
The rapid increase in digital financial transactions has intensified the need for robust fraud prevention mechanisms, especially in credit and debit card transactions. Traditional methods, while effective to an extent, often fall short in identifying complex, evolving fraud patterns. This paper explores the automation of fraud prevention using intelligent queue systems and regression testing, presenting an innovative approach that adapts to real-time transaction analysis. Intelligent queue systems prioritize transaction monitoring based on risk assessments derived from machine learning algorithms, ensuring that high-risk transactions are reviewed promptly and efficiently. Regression testing, meanwhile, serves as a continual validation tool, simulating various fraud scenarios to verify the system's accuracy in flagging fraudulent activities. By integrating these two components, the proposed model offers a dynamic, adaptive framework for detecting and preventing fraud, minimizing false positives, and optimizing transaction flow. This automation reduces manual intervention and operational costs, while maintaining high standards of transaction security. Results from case studies and simulations indicate that this approach can enhance fraud detection rates, streamline processing, and contribute to a more secure financial ecosystem.
Keywords:
Fraud prevention; Credit transactions; Debit transactions; Regression testing; Machine learning; Digital security
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0