Next-Generation AI and Cloud Architecture for Scalable Fraud Detection in SAP HANA
DOI:
https://doi.org/10.15662/IJARCST.2024.0701808Keywords:
AI-driven fraud detection, SAP HANA Cloud, cloud computing, machine learning, deep learning, banking systems, cybersecurity, DevSecOpsAbstract
The exponential growth of digital banking and cloud-native financial services has intensified the scale, velocity, and complexity of fraudulent activities, demanding intelligent and highly scalable detection mechanisms. Traditional fraud detection systems struggle to process high-volume, real-time transactions while maintaining accuracy and regulatory compliance. This paper presents a next-generation AI and cloud architecture for scalable fraud detection in SAP HANA–based banking systems. The proposed framework leverages SAP HANA Cloud’s in-memory computing capabilities combined with AI-driven machine learning and deep learning models to enable low-latency, real-time fraud analytics. Cloud-native microservices and DevSecOps pipelines support continuous model training, deployment, and monitoring, ensuring adaptability to evolving fraud patterns. The architecture integrates transactional analytics, behavioral profiling, and network security signals to enhance fraud intelligence and reduce false positives. Built-in security and governance mechanisms align with financial regulatory requirements while supporting elastic scalability and high availability. Experimental results indicate that the proposed AI-cloud framework significantly improves fraud detection accuracy, response time, and operational resilience compared to conventional on-premise and rule-based approaches. The study demonstrates how SAP HANA Cloud can serve as a robust foundation for next-generation, intelligent fraud detection in modern banking ecosystems.
References
1. Bolton, R. J., & Hand, D. J. (2002). Statistical fraud detection: A review. Statistical Science.
2. Sasidevi, J., Sugumar, R., & Priya, P. S. (2017). Balanced aware firefly optimization based cost-effective privacy preserving approach of intermediate data sets over cloud computing.
3. Thangavelu, K., Panguluri, L. D., & Hasenkhan, F. (2022). The Role of AI in Cloud-Based Identity and Access Management (IAM) for Enterprise Security. Los Angeles Journal of Intelligent Systems and Pattern Recognition, 2, 36-72.
4. Mani, K., Pichaimani, T., & Siripuram, N. K. (2021). RiskPredict360: Leveraging Explainable AI for Comprehensive Risk Management in Insurance and Investment Banking. Newark Journal of Human-Centric AI and Robotics Interaction, 1, 34-70.
5. Vijayaboopathy, V., Rao, S. B. S., & Surampudi, Y. (2023). Strategic Modernization of Regional Health Plan Data Platforms Using Databricks and Advanced Analytics Algorithms. Los Angeles Journal of Intelligent Systems and Pattern Recognition, 3, 172-208.
6. Sasidevi, J., Sugumar, R., & Priya, P. S. (2017). A Cost-Effective Privacy Preserving Using Anonymization Based Hybrid Bat Algorithm With Simulated Annealing Approach For Intermediate Data Sets Over Cloud Computing. International Journal of Computational Research and Development, 2(2), 173-181.
7. Sudhan, S. K. H. H., & Kumar, S. S. (2016). Gallant Use of Cloud by a Novel Framework of Encrypted Biometric Authentication and Multi Level Data Protection. Indian Journal of Science and Technology, 9, 44.
8. Anand, L., & Neelanarayanan, V. (2019). Feature Selection for Liver Disease using Particle Swarm Optimization Algorithm. International Journal of Recent Technology and Engineering (IJRTE), 8(3), 6434-6439.
9. Vaswani, A., et al. (2017). Attention is all you need. NeurIPS.
10. Kumbum, P. K., Adari, V. K., Chunduru, V. K., Gonepally, S., & Amuda, K. K. (2023). Navigating digital privacy and security effects on student financial behavior, academic performance, and well-being. Data Analytics and Artificial Intelligence, 3(2), 235–246.
11. Wu, Z., et al. (2021). Survey on graph neural networks. IEEE TNNLS.
12. Sculley, D., et al. (2015). Hidden technical debt in ML systems. NeurIPS.
13. Ribeiro, M. T., et al. (2016). LIME. KDD.
