The analytical company Elliptic, in cooperation with the Massachusetts Institute of Technology (MIT), investigated more than 200,000 transactions on the Bitcoin network for their connection with criminal activity.
In order to sort 203,769 transactions totaling $6 billion, the research team used a machine learning algorithm. The results were very controversial: 77% of transactions were not classified at all, 21% were recognized as legitimate and only 2% were illegal. Nevertheless, the researchers confidently state that artificial intelligence can significantly improve the effectiveness of the anti-money laundering procedure.
Recall that a month ago, a similar study was conducted by the company Chainalysis and, according to its data, the share of transactions in the Bitcoin network related to criminal activity in 2019 is estimated at about 1%. That is, in general, the data of Elliptic analysts almost do not differ from the results of the research conducted by Chainalysis. It should be noted that in 2012 this indicator was equal to 7%.
Law enforcement agencies often turn to Elliptic for help, especially when it is necessary to identify cases of illegal use of cryptocurrencies. The algorithms developed by the company help determine whether bitcoin is used for legitimate purposes, for example, by persons who do not have access to banking services, or unknown attackers are trying to use the cryptocurrency for illegal activities.
“Despite the high efficiency indicators of our algorithms, their use is still fraught with some problems, the biggest of which is false positives. The main goal of this study was to reduce the number of such triggers. However, the key conclusion is that such algorithms using machine learning are very effective for detecting illegal transactions, ” said Tom Robinson, co-founder of Elliptic.
Robinson also noted that in some cases, the system detected patterns for which it is difficult to find a description, but they corresponded to confirmed cases of illegal activity related to darknet markets, ransomware attacks and other criminal activity