According to CryptoPotato, blockchain analysis company Elliptic said that its researchers have made progress in using artificial intelligence (AI) to detect Bitcoin money laundering. The detailed report of this study was co-authored with researchers from the MIT-IBM Watson AI Lab. Elliptic used deep learning models to successfully identify illegal income deposited in cryptocurrency exchanges, new money laundering transaction patterns, and previously unidentified illegal wallets.

The company said the findings have been used to improve its products. Elliptic said it has worked with an undisclosed cryptocurrency exchange to test whether the technology can detect money laundering attempts through it. Of the 52 predicted "money laundering" subgraphs that ended with deposits to this exchange, 14 were confirmed by the exchange to be related to flagged users. On average, less than one account in every 10,000 was flagged, indicating that the model's performance is strong.