Bank Of Russia Signs Up Machine Learning To Bust Fraud

One of the world’s biggest banks has revealed it is leading the fight against criminals using state of the art AI technology.

The Bank of Russia has teamed up with Yandex Data Factory to use the latter’s machine learning services to identify unlicensed money lenders, and the websites hosting them.

So far, Yandex Data Factory’s custom search algorithm has helped to reveal 2,500 suspicious organisations, and played a significant role in spotting any inaccuracies, meaning that potentially fraudulent organisations will not be missed in the future.

Search and destroy

The system works by analysing key words across an existing Yandex database, which identified seven million web pages related to finance topics.

The algorithm is then able to assign a web page to its correct category, before identifying if an organisation is licenced, which Yandex says occurred correctly in 98 percent of cases.

Once a malicious organisation is identified, a report is automatically generated and sent to Bank of Russia with details of the organisations pulled from the search – from licensed providers to those with terminated licenses, along with organisations which never owned a licence and those whose licencing status could not be identified.

Using this information, bank employees are then able to act and feedback on the classification for each website identified, helping the algorithm to learn and improve.

“When it comes to consumer loans, illegal activity is rife and many people fall victims to scams,” noted Alexander Khaytin, COO for Yandex Data Factory. “By using machine learning to locate these illegal organisations and reporting them to the Bank of Russia, we can go a long way towards preventing fraudulent activity.”

Several UK banks have been forced to step up online security in recent months as cybercriminals increasingly target them in search of a major payout.

This includes NatWest, which tightened its online security precautions earlier this month after it emerged criminals were able to get access to accounts and transfer money without using any login details.

Are you a security pro? Try our quiz!