Blockchain Sleuth Elliptic Explores AI and Anti-Money Laundering Using 200M Bitcoin Transactions
Summary
Elliptic used a record 200 million Bitcoin transactions to train an AI model, detecting potential money laundering patterns. The larger dataset, named "Elliptic2," identified 122,000 labeled "subgraphs" linked to illicit activity. The AI model becomes more insightful with larger datasets. Suspicious subgraphs contained "peeling chains" and "nested services," common in money laundering. The AI approach automatically identifies new money laundering patterns as they emerge. Elliptic co-founder Tom Robinson highlighted the evolution of crypto laundering practices. The findings were detailed in a paper co-authored with researchers from the MIT-IBM Watson AI Lab.
