Systematic Review: Machine Learning Approaches for Detecting Illicit Activities in Bitcoin Transactions

Abstract

Blockchain networks are decentralized and offer pseudonymity, thus making illegal operations in Bitcoin very difficult to detect and stop. This work reviews recent machine learning approaches designed to spot these activities, focusing on the technical obstacles associated with class imbalance, unlabeled data, and how money laundering methods are rapidly becoming more advanced. Over a decade, reports from 2015 to 2025 were studied to analyze approaches that applied supervised learning, unsupervised clustering, and graph-based neural networks both individually and in mixed hybrid configurations. Important developments in related work are sophisticated blockchain data features, using ensembles to enhance performance, and systems for real-time automatic data processing. Analysis found that models using graph attention achieve over 40% improvement in performance compared to rule-based systems for finding unlawful activity. It further investigates methods for future privacy-preserving analytics, uncovering cross-chain criminals, and making regulations more compatible in the world of decentralized finance, to build better Anti-Money Laundering frameworks.