BLOCKCHAIN TRANSACTION ANALYSIS FOR MONEY LAUNDERING DETECTION USING MACHINE LEARNING

Abstract

Money laundering in blockchain transactions is identified through the application of machine learning in this investigation. The complexity of transaction patterns and pseudonymous identities in cryptocurrencies and decentralized financial systems make it more difficult to detect money laundering. Blockchain transaction data is analyzed, money laundering trends are identified, and structural and behavioral aspects are identified using supervised and unsupervised machine learning algorithms in the propose method. Predictive effectiveness is enhanced by network-based data, which includes transaction frequency, wallet connectivity, clustering coefficients, and temporal transaction behavior. The framework enhances detection accuracy and minimizes false positives by employing classification algorithms, anomaly detection, and feature engineering. The study posits that blockchain analytics powered by machine learning can enhance AML safeguards, assist organizations in adhering to regulations, and facilitate the development of decentralized financial systems.