Integrating AI-driven predictive analytics with devops for real-time fraud detection in financial institutions
1 Department of Management Information Systems, Lamar University, USA.
2 Department of Computer Science, Wrexham University, Wrexham, Wales, United Kingdom.
3 Department of information Technology, Georgia, Southern University, Statesboro, USA.
4 Central Michigan University, USA.
5 University of Sunderland, UK.
6 Department of Economics, Ohio University, USA.
7 MS Agile Project Management, Amberton University, Garland, Texas, USA.
8 Department of Information and Telecommunications System, Ohio University USA.
9 Department of Program Management, Canadore College, Canada.
10 Department of Criminal Justice, College of Public Affairs, University of Baltimore, Baltimore Maryland, USA.
11 Business Analytics, University of Dundee, United Kingdom.
Review Article
World Journal of Advanced Research and Reviews, 2023, 19(02), 1639-1653
Publication history:
Received on 13 July 2023; revised on 23 August 2023; accepted on 25 August 2023
Abstract:
Fraud detection remains a critical concern for financial institutions as the sophistication and frequency of fraudulent activities escalate, resulting in significant financial and reputational risks. Traditional rule-based systems are increasingly inadequate for combating dynamic and high-volume transactional fraud. This study investigates the integration of Artificial Intelligence (AI)-driven predictive analytics with DevOps methodologies to enhance real-time fraud detection capabilities in financial institutions. Employing a Systematic Literature Review (SLR) methodology, guided by the PRISMA framework, the study identified and analyzed five peer-reviewed articles published between 2015 and 2025 that addressed AI, DevOps, and fraud detection. Data were extracted and categorized into four thematic areas: AI technologies, DevOps practices, fraud detection applications, and integration challenges. The findings highlight that AI techniques, including machine learning and deep learning, enable real-time anomaly detection and risk scoring, significantly improving fraud detection accuracy. DevOps practices, such as Continuous Integration and Continuous Deployment (CI/CD), streamline the deployment and updating of AI models, ensuring adaptability to emerging fraud patterns. However, integration challenges persist, including data quality issues, model interpretability, organizational resistance, and compliance with regulatory frameworks. This research proposes a conceptual framework combining AI, DevOps, and real-time analytics to create scalable and adaptive fraud detection systems. The study concludes that integrating these technologies can enhance fraud detection precision, reduce false positives, and improve operational efficiency. Future research should focus on emerging AI techniques, advanced DevOps tools, and ethical governance to address existing gaps and support the widespread adoption of these solutions in financial institutions
Keywords:
Fraud detection; Artificial Intelligence (AI); DevOps methodologies; Predictive analytics; Machine learning; Real-time analytics
Full text article in PDF:
Copyright information:
Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0