Modernizing Anti-Money Laundering (AML) Data Pipelines Using Cloud-Native Architectures on Azure and Databricks
DOI:
https://doi.org/10.63282/3050-9416.IJAIBDCMS-V7I2P110Keywords:
Anti-Money Laundering (AML), Cloud-Native Architecture, Azure Databricks, Delta Lake, Real-Time Streaming, Financial Compliance, Machine Learning, Data GovernanceAbstract
Financial institutions must analyze large volumes of transactional data while complying with strict regulatory requirements aimed at preventing financial crime. Many existing Anti-Money Laundering (AML) systems rely on legacy infrastructures that use batch-oriented ETL pipelines and static rule-based monitoring, resulting in limited scalability and delayed fraud detection. This paper proposes a cloud-native AML data pipeline architecture implemented using Microsoft Azure and Azure Databricks. The framework integrates real-time data streaming, scalable data lake storage, and machine learning–based analytics to detect suspicious financial behavior. Data governance, lineage tracking, and automated compliance checks are embedded within the pipeline. The proposed approach enhances processing throughput, improves analytical accuracy, and enables financial institutions to respond more effectively to emerging financial crime patterns.
References
1. Financial Action Task Force, 'International Standards on Combating Money Laundering,' 2023.
2. FinCEN, 'Bank Secrecy Act AML Examination Manual,' 2023.
3. Microsoft Azure Architecture Center, Big Data Analytics Guide, 2024.
4. Databricks, 'Delta Lake Architecture Overview,' 2024.
5. J. Han, M. Kamber, Data Mining: Concepts and Techniques, 2011.
6. I. Goodfellow, Deep Learning, MIT Press, 2016.
7. S. Singh, 'Real-Time AML Analytics Using Big Data,' 2024.
8. T. White, Hadoop: The Definitive Guide, O’Reilly, 2015.
9. A. Gandomi, 'Big Data Analytics Methods,' 2024.
10. OECD Financial Crime Report, 2023.
11. IEEE Big Data Conference Proceedings, AML Analytics Paper, 2024.
12. World Bank Financial Integrity Report, 2023.
13. Gartner Report on Cloud Data Platforms, 2024.
14. McKinsey Global Banking Fraud Study, 2023.
15. NIST AI Risk Management Framework, 2024.
16. M. Weber et al., "Anti-Money Laundering in the Era of Big Data," IEEE Transactions on Big Data, 2022.
17. N. M. Alharbi, "Machine Learning Approaches for Financial Fraud Detection," IEEE Access, 2021.
