Article Sidebar

Download
PDF
Statistic
Read Counter : 282 Download : 102

Main Article Content

Abstract

The financial services industry faces mounting pressures to deliver real-time, personalized services while safeguarding sensitive user data under tight regulatory environments. Yet, prevailing AI systems in FinTech remain largely cloud dependent, which introduces latency bottlenecks, privacy exposure, and compliance risk.  Meanwhile, industry analyses suggest that Edge AI is rapidly becoming a foundational shift, with predictions that 60% of AI deployments will run partially on device by 2029. However, existing edge AI research often focuses on inference optimization, not full-stack orchestration of financial microservices, and therefore, lacks the integrated, decision-oriented intelligence that is required to operate wholly on the device. In this work, we present an architecture for on-device microservice orchestration of generative AI tailored for FinTech use cases.  Our system modularizes AI tasks, such as local LLM inference, fraud detection, biometric authentication, and credit scoring, into services coordinated via lightweight orchestrators (e.g. WASMEdge, Open Horizon). Unlike prior approaches, our system coordinates these services using lightweight WebAssembly-based runtimes, enabling secure, isolated, and efficient execution even on resource-constrained devices.  Sensitive data, such as transaction history and biometric templates, remains strictly local, with optional federated synchronization for global fraud pattern sharing. With quantized LLMs, we attain inference latency under 90ms, while local anomaly detection achieves 72% accuracy in simulated financial fraud scenarios. The architecture integrates modular microservices, privacy-first orchestration, and a hybrid federated intelligence layer and is among the first to present a decentralized, compliant, and performance-sensitive AI infrastructure for the FinTech of reality.

Keywords

Edge AI On-device inference FinTech Privacy-preserving AI Federated learning Low-latency AI

Article Details

How to Cite
Kishore Subramanya Hebbar, Vishal Sharma, & Maheshkar , J. A. . (2026). Edge-AI microservice orchestration for private, real-time generative FinTech applications . Future Technology, 5(2), 13–24. Retrieved from https://fupubco.com/futech/article/view/689
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. B. Saha, N. Rani, and S. K. Shukla, "Generative AI in
  2. Financial Institution: A Global Survey of Opportunities, Threats, and Regulation," arXiv preprint arXiv:2504.21574, Apr. 2025. https://arxiv.org/abs/2504.21574
  3. S. Siam, N. S. Mohamed, and A. S. Abdelaty, "Hybrid feature selection framework for enhanced credit card fraud detection," PLoS ONE, vol. 20, no. 7, e0326975, 2025. https://doi.org/10.1371/journal.pone.0326975
  4. Xu, J., Wang, H., Zhong, Y., Qin, L., and Cheng, Q. (2024). Predict and Optimize Financial Services Risk Using AI-driven Technol-ogy. Academic Journal of Science and Technology, 10(1), 299–304. https://doi.org/10.54097/6zrqef25
  5. Moharrak, M., and Mogaji, E. (2024). Generative AI in banking: em-pirical insights on integration, challenges and opportunities in a regulated industry. International Journal of Bank Marketing, 43(4), 871–896. https://doi.org/10.1108/ijbm-08-2024-0490
  6. Han, L., Lei, M., He, G., Li, Y., and Zhao, Y. (2025). Energy-efficient cloud-edge collaborative model integrating digital twins and machine learning for scalable and adaptive distributed net-works. Sustainable Computing: Informatics and Systems, 47, 101157. https://doi.org/10.1016/j.suscom.2025.101157
  7. Benedict, S. (2024). Edge-AI applications. Edge Intelligence, 11-1-11–28. https://doi.org/10.1088/978-0-7503-5593-3ch11
  8. Zhan, S., Huang, L., Luo, G., Zheng, S., Gao, Z., and Chao, H.-C. (2025). A Review on Federated Learning Architectures for Privacy-Preserving AI: Lightweight and Secure Cloud–Edge–End Collaboration.
  9. Electronics, 14(13), 2512. https://doi.org/10.3390/electronics14132512
  10. Jethwani, K., & Ramchandani, K. (2021). Odds & Edge: on the edge. Emerald Emerging Markets Case Studies, 11(4), 1–24. https://doi.org/10.1108/eemcs-04-2021-0096
  11. Bhatia Sarin, A. (2024). Understanding of Decentralized Finance and Tokenization in FinTech. Decentralized Finance and Tokenization in FinTech, 285–309. https://doi.org/10.4018/979-8-3693-3346-4.ch016
  12. Xu, D., Duan, L., Zhu, J., and Zhu, H. (2025). Decentralized LLM Deployment in Mobile Edge Computing Networks. https://doi.org/10.36227/techrxiv.176108088.85561999/v1
  13. Pilz, K. F., Sanders, J., Rahman, R., & Heim, L. (2025). Trends in AI supercomputers. arXiv preprint arXiv:2504.16026.
  14. Ramamoorthi, V. (2023). Exploring AI-Driven Cloud-Edge Orchestration for IoT Applications. Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol, 9, 385-393.
  15. Vishwakarma, S. K. (2025). Sustainable aviation fuel (SAF) procurement challenges. Journal of Innovation and Sustainable Energy Management. https://www.jisem-journal.com/index.php/journal/article/view/9420
  16. Deng, K., Wang, H., Shu, Z., Gu, T., Xiao, Y., Liu, E., & Zhao, Z. (2025). System-on-Chip Test and Characterization: A Review. IEEE Transactions on Instrumentation and Measurement.
  17. Nagaraj, V. (2025). Automating test vector validation for silicon verification at scale. International Journal of Engineering and Applied Sciences (IJEAS). https://gprjournals.org/journals/index.php/ijea/article/view/358
  18. Zhang, R., Jiang, H., Wang, W., & Liu, J. (2025). Optimization Methods, Challenges, and Opportunities for Edge Inference: A Comprehensive Survey. Electronics, 14(7), 1345.
  19. Nalla, S., & Nagarajan, G. (2025). Continual Learning-Based Regression Testing for Scalable VLSI Verification Across Hierarchical Design Layers. Sustainable Computing: Informatics and Systems, 10
  20. Mohanty, A., Mohanty, S. K., & Mohapatra, A. G. (2024). Real-Time Monitoring and Fault. The AI Cleanse: Transforming Wastewater Treatment Through Artificial Intelligence: Harnessing Data-Driven Solutions, 165.
  21. Rane, N. (2023). Integrating leading-edge artificial intelligence (AI), internet of things (IOT), and big data technologies for smart and sustainable architecture, engineering and construction (AEC) industry: Challenges and future directions. Engineering and Construction (AEC) Industry: Challenges and Future Directions (September 24, 2023).
  22. ovescu, D., and Tudose, C. (2024). Real-Time Docu-ment Collaboration System Using Orchestrated Containers. https://doi.org/10.20944/preprints202408.1228.v1
  23. Fernandez, J.-M., Vidal, I., & Valera, F. (2019). Enabling the Orchestration of IoT Slices through Edge and Cloud Microservice Platforms. Sensors, 19(13), 2980. https://doi.org/10.3390/s19132980
  24. Subedi, P., Hao, J., Kim, I. K., and Ramaswamy, L. (2021). AI Multi-Tenancy on Edge: Concurrent Deep Learning Model Executions and Dynamic Model Placements on Edge Devices. 2021 IEEE 14th International Conference on Cloud Computing (CLOUD), 31–42. https://doi.org/10.1109/cloud53861.2021.00016
  25. Atmaja, P., Maulana, D. I., and Adiono, T. (2020). AI-based Customer Behavior Analytics System using Edge Computing Device. 2020 International Conference on Electronics, Information, and Communication (ICEIC), 1–2. https://doi.org/10.1109/iceic49074.2020.9051138
  26. Zhong, Y., & Deng, Y. (2015). A Survey on Keystroke Dynamics Biometrics: Approaches, Advances, and Evaluations. Recent Advances in User Authentication Using Keystroke Dynamics Biometrics, 1–22. https://doi.org/10.15579/gcsr.vol2.ch1
  27. IEEE Computational Intelligence Society, "IEEE-CIS Fraud Detection Dataset," 2019. https://www.kaggle.com/competitions/ieee-fraud-detection
  28. Whitesell, S., and Richardson, R. (2025). Healthy Microservices. Pro Microservices in .NET 10, 219–238. https://doi.org/10.1007/979-8-8688-2049-6_10
  29. Ouadrhiri, A. E., & Abdelhadi, A. (2022). Differential Privacy for Deep and Federated Learning: A Survey. IEEE Access, 10, 22359–22380. https://doi.org/10.1109/access.2022.3151670
  30. Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models. (2025). https://doi.org/10.7249/rra3797-1
  31. Shuai Fang. (2024). Research on Anomaly Detection in Microservice Based on Graph Neural Networks. Computer Fraud and Security, 44–56. https://doi.org/10.52710/cfs.88
  32. A, M. (2025). Real-time Biometric Authentication on Edge Devices Us-ing AI. https://doi.org/10.2139/ssrn.5276971
  33. Bian, J. (n.d.). Indirect-Communication Federated Learning via Mobile Transporters-supp1-3527405.pdf. https://doi.org/10.1109/tmc.2025.3527405/mm1
  34. Dasari, V. L., Mokkapati, R., Lavanya, K., and Chetan, G. (2024). Protecting AI-Enabled Industrial Engineering in Cloud and Edge Environments. Industrial Internet of Things Security, 1–34. https://doi.org/10.1201/9781003466284-1
  35. Tarun Kaniganti, S. (2021). Architecting Privacy-First: AI-Enhanced Compliance Frameworks in AWS-Based Healthcare Analytics. International Journal of Science and Research (IJSR), 10(12), 1517–1527. https://doi.org/10.21275/sr24806050147
  36. Hosseinalibeiki, H., and Sepehrzad, R. (2025). Hybrid Llm-Based Emergency Management with Constraint-Aware Edge Deployment in Intelligent Transportation System. https://doi.org/10.2139/ssrn.5359892