Blockchain analytics firm Elliptic has released a public dataset of bitcoin transactions associated with money laundering, in partnership with the Massachusetts Institute of Technology (MIT), the company announced in a press release.
The so-called Elliptic Data Set was developed with data from over 200,000 Bitcoin node transactions, with a total value of $6 billion. According to the team, this is “the world’s largest set of labeled transaction data publicly available in any cryptocurrency”, and was created to see if artificial intelligence could assist current anti-money laundering (AML) procedures. The product is not only designed to help users identify illicit transactions more efficiently, but could also reduce compliance costs. Tom Robinson, Chief Scientist and co-founder of Elliptic, said in the press release:
“Elliptic uses a range of advanced techniques, including machine learning, to facilitate financial crime detection in cryptocurrencies. Our work with researchers from the MIT-IBM Watson AI Lab builds on this, to ensure that our clients have access to the most accurate and effective insights available, reducing their compliance costs and ensuring that their services are not exploited by criminals.”
According to the data set, around 2 percent of the 200,000 Bitcoin transactions were found to be illicit, while 21 percent were deemed as lawful. We have to point out here, that 77 percent still remain as unclassified, and that since the network launch in 2009, there have been close to 440 million transactions. Robinson has also said that:
“A big problem with compliance, in general, is false positives. A big part of this research is minimizing the number of false positives. The key finding is that machine learning techniques are very effective at finding transactions that are illicit.”
A new paper, called “Anti-Money Laundering in Bitcoin: Experiments with Graph Convolutional Networks for Financial Forensics”, which was co-authored by Elliptic scientists and researchers from the MIT-IBM Watson AI Lan will be presented today, 5 August, at the Anomaly Detection in Finance workshop of the Knowledge Discovery and Data Mining Conference. Presenting the paper will be Giacomo Domeniconi and Mark Weber, who also released details around the group’s study and how they used machine learning software to analyse the Bitcoin transactions. Weber commented:
“Graph convolutional networks are still a young class of methods, and we’re in the early days in these experiments, but we do believe GCN’s power to capture the relational information in these large, complex transaction networks could prove valuable for anti-money laundering”
In the ever-evolving world of online entertainment, Bitcoin gaming is no longer just a niche interest for cryptocurrency enthusiasts. With the rise of blockchain technology, Bitcoin games have become a significant trend, drawing in players from all corners of the globe with the promise of transparent gaming experiences and financial incentives. As this new frontier […]