Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199785,
        author = {Rohan Jeyan and P. Uma},
        title = {SecurePay: A Multi-Layered AI Framework for Intelligent Fraud Detection and Adaptive Security in Digital Payment Systems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15696-15705},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199785},
        abstract = {The rapid growth of digital payment platforms has introduced significant challenges around transaction fraud, user authentication, and personalized financial services. Existing solutions often address these concerns in isolation, relying on single-model architectures that lack adaptability and layered protection. This paper presents SecurePay, a mobile payment system that integrates multiple AWS AI/ML services into a cohesive, multi-layered security and intelligence framework. The system combines gradient-boosted decision trees on Amazon SageMaker for real-time fraud scoring and promotional recommendation, Amazon Rekognition for biometric face authentication, and Amazon Bedrock with large language models for natural language transaction search, automated categorization, and personalized spending insights. All AI service calls are routed through serverless edge functions with rule-based fallbacks, isolating credentials from the client. Evaluation on synthetic datasets shows F1 = 1.00 and AUC-ROC = 1.00 for fraud detection with a median pipeline latency of 846 ms, and a macro F1 of 1.00 for promotional recommendation across five categories. Cost analysis shows the full AI stack operates at approximately $94.67 per month for 10,000 transactions.},
        keywords = {digital payments, fraud detection, biometric authentication, machine learning, cloud computing, serverless architecture, XGBoost, large language models.},
        month = {April},
        }