A Privacy-Preserving Federated AI Architecture on AWS for Financial Forecasting and Healthcare Analytics Using LLMs and Java Microservices
DOI:
https://doi.org/10.15662/IJEETR.2025.0705005Keywords:
Federated learning, AWS, privacy preserving, financial forecasting, healthcare analytics, SageMaker, differential privacy, secure aggregation, distributed machine learningAbstract
Federated Machine Learning (FL) is a decentralized machine learning paradigm that enables multiple parties to collaboratively train shared models while keeping their data localized, thus preserving privacy and complying with data protection regulations. This research investigates the design, implementation, and evaluation of federated learning systems on Amazon Web Services (AWS) for privacy‑preserving applications in two sensitive domains: financial forecasting and healthcare analytics.
By leveraging AWS services such as Amazon SageMaker, Amazon Elastic Kubernetes Service (EKS), and cloud infrastructure security features, the proposed framework supports collaborative model training across institutions (e.g., banks and hospitals) without centralizing raw data. Privacy‑enhancing techniques—including differential privacy, secure aggregation, and encrypted communication—are integrated to mitigate inference attacks and regulatory risks.
The financial forecasting component focuses on risk estimation and credit scoring models across participating banks, while the healthcare analytics component targets predictive diagnostics and patient outcome predictions across hospitals.
Experimental results show federated models achieving performance comparable to centralized baselines while preserving data privacy and reducing compliance burdens. Operational metrics such as model accuracy, communication overhead, and scalability under AWS infrastructure are analyzed.
The study demonstrates that AWS‑based federated learning architectures provide a viable and scalable foundation for cross‑institutional privacy‑preserving AI applications in finance and healthcare. (Amazon Web Services, Inc.)
References
1. Bonawitz, K., Eichner, H., Grieskamp, W., et al. (2019). Towards federated learning at scale: System design. In Proceedings of SysML
2. Tamizharasi, S., Rubini, P., Saravana Kumar, S., & Arockiam, D. Adapting federated learning-based AI models to dynamic cyberthreats in pervasive IoT environments.
3. Poornima, G., & Anand, L. (2024, May). Novel AI Multimodal Approach for Combating Against Pulmonary Carcinoma. In 2024 5th International Conference for Emerging Technology (INCET) (pp. 1-6). IEEE.
4. Sugumar, R. (2023, September). A Novel Approach to Diabetes Risk Assessment Using Advanced Deep Neural Networks and LSTM Networks. In 2023 International Conference on Network, Multimedia and Information Technology (NMITCON) (pp. 1-7). IEEE.
5. Bansal, R., Chandra, R., & Lulla, K. (2025). Understanding and Mitigating Strategies for Large Language Model (LLMs) Hallucinations in HR Chatbots. International Journal of Computational and Experimental Science and Engineering, 11(3).
6. Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., & Yang, Q. (2019). SecureBoost: A lossless federated learning framework. arXiv. (arXiv)
7. Daram, S. (2025). Federated learning in medical AI: Privacy preserving data sharing for collaborative healthcare research. Int’l Journal AI Data Science Machine Learning. (IJAI Data Science & ML)
8. Vimal Raja, G. (2025). Context-Aware Demand Forecasting in Grocery Retail Using Generative AI: A Multivariate Approach Incorporating Weather, Local Events, and Consumer Behaviour. International Journal of Innovative Research in Science Engineering and Technology (Ijirset), 14(1), 743-746.
9. Sen, S., Kurni, M., Krishnamaneni, R., & Murthy, A. (2024, December). Improved Bi-directional Long Short-Term Memory for Heart Disease Diagnosis using Statistical and Entropy Feature Set. In 2024 9th International Conference on Communication and Electronics Systems (ICCES) (pp. 1331-1337). IEEE.
10. Nagarajan, G. (2024). Cloud-Integrated AI Models for Enhanced Financial Compliance and Audit Automation in SAP with Secure Firewall Protection. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 7(1), 9692-9699.
11. Koh, C. W. H. B. (2025). AI-Based Cybersecurity and Fraud Analytics for Healthcare Data Integration in Cloud Banking Ecosystems. International Journal of Engineering & Extended Technologies Research (IJEETR), 7(6), 11021-11028.
12. Vasugi, T. (2022). AI-Enabled Cloud Architecture for Banking ERP Systems with Intelligent Data Storage and Automation using SAP. International Journal of Engineering & Extended Technologies Research (IJEETR), 4(1), 4319-4325.
13. Kumar, R. K. (2024). Real-time GenAI neural LDDR optimization on secure Apache–SAP HANA cloud for clinical and risk intelligence. IJEETR, 8737–8743. https://doi.org/10.15662/IJEETR.2024.0605006
14. Vijayaboopathy, V., & Dhanorkar, T. (2021). LLM-Powered Declarative Blueprint Synthesis for Enterprise Back-End Workflows. American Journal of Autonomous Systems and Robotics Engineering, 1, 617-655.
15. Panguluri, L. D., Mohammed, S. B., & Pichaimani, T. (2023). Synthetic Test Data Generation Using Generative AI in Healthcare Applications: Addressing Compliance and Security Challenges. Cybersecurity and Network Defense Research, 3(2), 280-319.
16. Mehta, A. (2022). Privacy preserving federated learning on AWS using NVIDIA FLARE. Int’l Journal AI Data Science Machine Learning. (IJAI Data Science & ML)
17. Christadoss, J., & Panda, M. R. (2025). Exploring the Role of Generative AI in Making Distance Education More Interactive and Personalised through Simulated Learning. Futurity Proceedings, (4), 114-127..
18. Meka, S. (2024). Securing Instant Payments: Implementing Fraud Prevention Frameworks with AVS and OTP Validation. Journal Code, 1763, 4821.
19. Joyce, S., Anbalagan, B., Pasumarthi, A., & Bussu, V. R. R. PLATFORM RELIABILITY IN MICROSOFT AZURE: ARCHITECTURE PATTERNS AND FAULT TOLERANCE FOR ENTERPRISE WORKLOADS.
20. Shokri, R., & Shmatikov, V. (2015). Privacy preserving deep learning. ACM CCS.
21. Sheller, M. J., et al. (2020). Federated learning in medical imaging. Medical Image Analysis.
22. Kagalkar, A., Kabade, S., Chaudhri, B., & Sharma, A. (2023). AI-Driven Automation for Death Claim Processing In Pension Systems: Enhancing Accuracy and Reducing Cycle Time. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 4(4), 105-110.
23. Zerine, I., Hossain, A., Hasan, S., Rahman, K. A., & Islam, M. M. (2024). AI-Driven Predictive Analytics for Cryptocurrency Price Volatility and Market Manipulation Detection. Journal of Computer Science and Technology Studies, 6(2), 209-224
24. Sugumar, R. (2024). Next-Generation Security Operations Center (SOC) Resilience: Autonomous Detection and Adaptive Incident Response Using Cognitive AI Agents. International Journal of Technology, Management and Humanities, 10(02), 62-76.
25. Kusumba, S. (2024). Data Integration: Unifying Financial Data for Deeper Insight. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 7(1), 9939-9946.
26. Praveen Kumar Reddy Gujjala. (2022). Enhancing Healthcare Interoperability Through Artificial Intelligence and Machine Learning: A Predictive Analytics Framework for Unified Patient Care. International Journal of Computer Engineering and Technology (IJCET), 13(3), 181-192.
27. Chukkala, R. (2025). Unified Smart Home Control: AI-Driven Hybrid Mobile Applications for Network and Entertainment Management. Journal of Computer Science and Technology Studies, 7(2), 604-611.
28. Oleti, Chandra Sekhar. (2023). Credit Risk Assessment Using Reinforcement Learning and Graph Analytics on AWS. World Journal of Advanced Research and Reviews. 20. 1399-1409. 10.30574/wjarr.2023.20.1.2084.
29. Girdhar, P., Virmani, D., & Saravana Kumar, S. (2019). A hybrid fuzzy framework for face detection and recognition using behavioral traits. Journal of Statistics and Management Systems, 22(2), 271-287.
30. Poornima, G., & Anand, L. (2024, April). Effective Machine Learning Methods for the Detection of Pulmonary Carcinoma. In 2024 Ninth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) (pp. 1-7). IEEE.
31. Adari, V. K., Chunduru, V. K., Gonepally, S., Amuda, K. K., & Kumbum, P. K. (2023). Ethical analysis and decision-making framework for marketing communications: A weighted product model approach. Data Analytics and Artificial Intelligence, 3 (5), 44–53.
32. Sudhakara Reddy Peram, Praveen Kumar Kanumarlapudi, Sridhar Reddy Kakulavaram. (2023). Cypress Performance Insights: Predicting UI Test Execution Time Using Complexity Metrics. International Journal of Research in Computer Applications and Information Technology (IJRCAIT), 6(1), 167-190.
