Economic Criminology in the Digital Era: Algorithmic Detection of Money Laundering and Tax Evasion in Blockchain Networks

Abstract

The rapid expansion of blockchain-based financial systems has fundamentally transformed the structure of economic crime. While distributed ledger technologies provide unprecedented transparency, they simultaneously enable pseudonymous interactions that can be exploited for illicit financial activities, including money laundering and tax evasion. This paper develops a theoretical and computational framework for detecting illicit financial behavior in blockchain networks. By integrating economic criminology, graph-based analysis, and machine learning techniques, it proposes a composite detection model capable of identifying suspicious transaction patterns through structural and behavioral indicators. The study argues that blockchain-based financial crime is not hidden but structurally embedded within transparent systems, requiring algorithmic interpretation rather than traditional investigative approaches. The findings highlight the importance of scalable, data-driven enforcement mechanisms and coordinated regulatory responses in addressing financial crime in decentralized environments.