Federated Data Mesh with AI Governance: A Framework for Distributed Banking Analytics with Intelligent Policy Enforcement
DOI:
https://doi.org/10.22399/ijcesen.5148Keywords:
Data Mesh, Federated Learning, Data Governance, Distributed Systems, Machine Learning, Banking TechnologyAbstract
Traditional centralized data platforms face fundamental scalability constraints as banking institutions expand their analytical workloads, domain boundaries multiply, and regulatory obligations intensify—creating systemic bottlenecks in data access, innovation throughput, and the application of domain expertise to business-critical decisions. Data mesh architectures decentralize data ownership to domain teams, positioning data as managed products with defined quality, accessibility, and discoverability contracts; yet this decentralization introduces a new class of governance challenges, encompassing how to assure consistent quality across autonomous domains, how to enforce regulatory compliance without imposing centralized control, and how to prevent fragmentation while enabling genuine domain autonomy. The federated data mesh framework presented here addresses these tensions through an integrated suite of machine learning capabilities—combining federated learning for privacy-preserving collaborative model development, graph neural networks for automated lineage and impact discovery across distributed products, reinforcement learning for intelligent resource allocation and query routing, natural language processing for automated metadata enrichment, and distributed policy enforcement enhanced with machine learning-based anomaly detection. Deployed across banking platforms spanning retail banking, wealth management, and commercial lending domains, the framework delivers substantial improvements in data product velocity, data quality, regulatory compliance, and analyst time-to-insight, establishing a validated architecture for data mesh governance at production scale in regulated financial services environments. The seven-stage asynchronous orchestration model, closed governance feedback loops, and domain-level resilience mechanisms introduced here collectively represent a reproducible blueprint for decentralized data governance at enterprise scale.
References
[1] Pegdwendé Sawadogo and Jérôme Darmont, "On data lake architectures and metadata management," Journal of Intelligent Information Systems, 2021. https://link.springer.com/article/10.1007/s10844-020-00608-7
[2] Athira Nambiar and Divyansh Mundra, "An Overview of Data Warehouse and Data Lake in Modern Enterprise Data Management," Big Data Cogn. Comput., 2022. https://www.mdpi.com/2504-2289/6/4/132 DOI: https://doi.org/10.3390/bdcc6040132
[3] Viraaji Mothukuri, et al., "A survey on security and privacy of federated learning," Future Generation Computer Systems, 2021. https://www.sciencedirect.com/science/article/abs/pii/S0167739X20329848 DOI: https://doi.org/10.1016/j.future.2020.10.007
[4] Sanghoon Jeon and Huy Kang Kim, "AutoVAS: An automated vulnerability analysis system with a deep learning approach," Computers & Security, 2021. https://www.sciencedirect.com/science/article/abs/pii/S0167404821001322 DOI: https://doi.org/10.1016/j.cose.2021.102308
[5] Zonghan Wu, et al., "A Comprehensive Survey on Graph Neural Networks," IEEE Transactions on Neural Networks and Learning Systems, 2020. https://ieeexplore.ieee.org/document/9046288
[6] Jie Zhou, et al., "Graph neural networks: A review of methods and applications," AI Open, 2020. https://www.sciencedirect.com/science/article/pii/S2666651021000012 DOI: https://doi.org/10.1016/j.aiopen.2021.01.001
[7] Yang Liu, et al., "A Secure Federated Transfer Learning Framework," IEEE Intelligent Systems, 2020. https://ieeexplore.ieee.org/document/9076003
[8] Chen Zhang, et al., "A survey on federated learning," Knowledge-Based Systems, 2021. https://www.sciencedirect.com/science/article/abs/pii/S0950705121000381 DOI: https://doi.org/10.1016/j.knosys.2021.106775
[9] Soham Das, et al., "Bi-Level Prediction Model for Screening COVID-19 Patients Using Chest X-Ray Images Bi-Level Prediction Model for Screening COVID-19 Patients Using Chest X-Ray Images," Big Data Research, 2021. https://www.sciencedirect.com/science/article/pii/S2214579621000502 DOI: https://doi.org/10.1016/j.bdr.2021.100233
[10] Marijn Janssen, et al., "Data governance: Organizing data for trustworthy Artificial Intelligence," Government Information Quarterly, 2020. https://www.sciencedirect.com/science/article/abs/pii/S0740624X20302719 DOI: https://doi.org/10.1016/j.giq.2020.101493
[11] Peter Kairouz and H. Brendan McMahan, "Advances and Open Problems in Federated Learning," Foundations and Trends in Machine Learning, 2021. https://www.emerald.com/ftmal/article-abstract/14/1-2/1/1332154/Advances-and-Open-Problems-in-Federated-Learning?redirectedFrom=fulltext DOI: https://doi.org/10.1561/2200000083
[12] Nicola Rieke, et al., "The future of digital health with federated learning," npj Digital Medicine, 2020. https://www.nature.com/articles/s41746-020-00323-1 DOI: https://doi.org/10.1038/s41746-020-00323-1
[13] Nicholas W. Miller, "From the High Plains and Deserts: A new look at getting renewable energy from remote sources to load centers," IEEE Electrification Magazine, 2022. https://ieeexplore.ieee.org/document/9729124 DOI: https://doi.org/10.1109/MELE.2021.3139250
[14] Dinh C. Nguyen, et al., "Federated Learning for Internet of Things: A Comprehensive Survey," IEEE Communications Surveys & Tutorials, 2021. https://ieeexplore.ieee.org/document/9415623 DOI: https://doi.org/10.1109/COMST.2021.3075439
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
