Fintech firm Revolut has implemented new machine-learning technology that has cut card fraud significantly, the company said.
The firm said it is using algorithms, machine learning and computational techniques to protect against card fraud and money laundering, claiming to see a fourfold reduction in fraud in two months.
The technology can develop predictions around customer behaviour that can be used to identify new card fraud patterns without human intervention. It applies complex mathematical models to large datasets to spot any anomalies, and has now developed a real-time system that is based on identifying abnormal spending habits. The system will freeze card payments until the customer verifies in the app that the spending is genuine.
Revolut said it has been using the system since early August, and has reduced fraud in e-commerce payments, card cloning and card theft.
Money laundering
To help combat money laundering, Revolut has launched new machine-learning technology that calculates a risk score for users, processing transactions in Revolut live. If the score exceeds a set threshold, customers will have to verify the activity with additional paperwork.
Nik Storonsky, founder and CEO of Revolut, said several banks have already approached Revolut to buy the technology.
“What we can accurately display in 10 minutes would typically take a large bank over an hour to establish with their current manual processes,” he said. “If you’re on a mission to reach tens of millions of customers and scale your business globally, then you cannot rely solely on manual human processes to effectively protect your customers against financial crime, especially as criminals are becoming more savvy in their tactics.”
Revolut has signed up three million customers in Europe, and has plans for several other markets, including United States, Canada, Australia, Singapore and Hong Kong.
