Detection of money laundering in bitcoin transactions

Combating Money laundering through cryptocurrencies has become a more challenging task due to the inherent anonymity of cryptocurrency transactions and the absence of centralized control authorities to apply known defensive laws and policies such as Know Your Customer (KYC) and Know Your Business (KYB) measures. This has led to an increase in number of cybercrimes that involve cryptocurrency as a payment method for illicit acts and a way to hide sources of dirty money. Therefore, researchers have been discovering new anti-money laundry detection and prevention techniques to combat these cybercrimes. In this work, we present an efficient anti-money laundry system that analyzes the transactions of cryptocurrency to learn data patterns that can identify licit and illicit transactions. Our system utilizes known machine learning mechanisms such as shallow neural networks and decision trees to construct the classification models. Without loss of generality, we evaluate our system on a recent bitcoin anti-money laundry dataset, the elliptic dataset, and use the classification accuracy as a performance indicator. Our analysis shows that shallow neural networks and decision trees achieve classification accuracy capped at 89.9% and 93.4%, respectively.