UK Department of Work and Pensions Uses AI To Crack Down On Fraud

Benefit fraud, particularly by criminal gangs, costs the Department of Work and Pensions (DWP) in the United Kingdom almost £2.1 billion (~$2.6 billion US) in 2016 – a rise of £200 million in just one year. Over the last year, Ministers of the Department for Work and Pensions (DWP) have extensively tested the use of artificial intelligence to automate claims processing and fight fraud within their department.

The algorithms look for patterns in claims such as the same phone number or applications written in the same style and identifies possible issues faster than human investigators could. Once a claim is flagged as suspicious, a human investigator takes over to determine if the claim is in fact fraudulent. Artificial intelligence algorithms are also used to search social media accounts to uncover inconsistencies in the stories people tell on social media and the claims they are making for benefits.

The department’s annual report states it is focusing on “organized attacks on the welfare system”, cracking down on criminals committing large-scale benefits fraud.

“We have developed cutting-edge artificial intelligence to crack down on organized criminal gangs committing large-scale benefit fraud,” the report states. “We carried out trials using algorithms that can identify different types of organized attacks on the welfare system. The algorithms reveal fake identity-cloning techniques that are commonly used by fraudsters, which are only detectable by intelligent computer programmes capable of searching for anomalies in billions of items of data.”

The DWP is also bringing together its existing data acquisition, risk analysis, and intelligence gathering capabilities to form a risk and intelligence service, which assigns risks to benefit claims, allowing the department to prioritize.