A Comprehensive Framework to Identify and Prevent Money Laundering in Decentralized Finance Using Big Data Analytics

Abstract

Objective: This research aims to develop a comprehensive framework to identify and prevent money laundering in Decentralized Finance (DeFi) by leveraging big data analytics, integrating advanced machine learning algorithms, and network analysis techniques to address the challenges of pseudonymity and decentralization inherent to this ecosystem.
Research Design & Methods: This research utilizes a mixed method approach with machine learning analysis based on Elliptic Dataset and qualitative policy study, applying graph models and classification algorithms to detect illegal transactions with precision in the context of imbalanced data.
Findings: The results show that the MLP and GCN models achieve high accuracy (98% and 97.3%) and excellent recall (99.5% and 99.4%) on the Elliptic Dataset, significantly outperforming traditional methods. Exploratory data analysis and graph visualization confirmed that illegal transactions form denser clusters and more complex paths, indicating a layering pattern.
Implications and Recommendations: Theoretically, this research extends the application of big data and graph theory to new financial systems, providing a blueprint for future RegTech and FinTech research. Practically, the framework offers tangible tools for regulators, law enforcement, and DeFi platforms to enhance AML capabilities, supporting the development of real-time monitoring tools and risk assessment models.
Contribution and Value Added: The main contribution of this research is the development of a robust and adaptive big data analytics-based AML framework, which effectively addresses the unique challenges of DeFi.