Blockchain analytics firm Elliptic uses 200 million Bitcoin transactions to explore artificial intelligence and anti-money laundering

Blockchain analytics firm Elliptic says it discovered potential money laundering patterns on the Bitcoin blockchain after training an artificial intelligence (AI) model using a record 200 million transactions. In a paper co-authored with researchers at MIT-IBM's Watson AI Lab, Elliptic said Elliptic used the transactions to learn a set of "shapes" money laundering exhibits in cryptocurrencies and accurately classify new criminal activity.
"The money laundering techniques identified by the model have been identified because of their prevalence in Bitcoin," Tom Robinson, co-founder of Elliptic, said in an email. "Cryptocurrency money laundering practices evolve over time as they are no longer effective, but one advantage of artificial intelligence/deep learning methods is that new money laundering patterns are automatically identified as they emerge."