Characterizing and Detecting Money Laundering Activities on the Bitcoin Network

TL;DR

This paper analyzes Bitcoin transaction graphs over three years to identify features distinguishing money laundering activities from regular transactions, proposing classifiers that achieve over 92% accuracy in detection.

Contribution

It introduces a novel graph-based classification approach using node2vec embeddings to effectively detect money laundering in Bitcoin transactions.

Findings

Node2vec classifier achieves 92.29% accuracy.

Laundering transactions differ mainly in output values and neighborhood info.

Classifiers can discover unknown laundering services with ensemble techniques.

Abstract

Bitcoin is by far the most popular crypto-currency solution enabling peer-to-peer payments. Despite some studies highlighting the network does not provide full anonymity, it is still being heavily used for a wide variety of dubious financial activities such as money laundering, ponzi schemes, and ransom-ware payments. In this paper, we explore the landscape of potential money laundering activities occurring across the Bitcoin network. Using data collected over three years, we create transaction graphs and provide an in-depth analysis on various graph characteristics to differentiate money laundering transactions from regular transactions. We found that the main difference between laundering and regular transactions lies in their output values and neighbourhood information. Then, we propose and evaluate a set of classifiers based on four types of graph features: immediate neighbours, curated features, deepwalk embeddings, and node2vec embeddings to classify money laundering and regular transactions. Results show that the node2vec-based classifier outperforms other classifiers in binary classification reaching an average accuracy of 92.29% and an F1-measure of 0.93 and high robustness over a 2.5-year time span. Finally, we demonstrate how effective our classifiers are in discovering unknown laundering services. The classifier performance dropped compared to binary classification, however, the prediction can be improved with simple ensemble techniques for some services.