AI Case Study

The UK government identifies welfare and state benefits fraud with artificial intelligence

The Department for Work and Pensions (DWP) have tested AI to automate claims processing and eliminate fraudulent applications within their department. The AI algorithms identify patterns in claims such as same telephone numbers or similar-looking applications. The algorithms also scour social media accounts to confirm that the stories people tell are consistent and valid. If a claim is flagged as suspicious by the system, a human investigator takes over. The employment of the technology ultimately protects taxpayers’ money and ensures that benefits are given to the people who actually need them.

Industry

Public And Social Sector

Government

Project Overview

"Ministers of the Department for Work and Pensions (DWP) have rolled out and tested AI to automate claims processing and fight fraud within their department. Over the last year, the department unleashed artificial intelligence algorithms to track down large-scale corruption of the benefit and welfare program to stop criminal gangs who are responsible for extremely large losses. Ultimately, this effort protects taxpayers’ money and gets the benefits to those who they are intended for.

The algorithms look for patterns in claims such as the same phone number or applications written in the same style. Once a claim is flagged as suspicious, a human investigator takes over to determine if the claim is in fact fraudulent.

AI identifies possible issues faster than human investigators who in the past would have to assess every claim. Therefore, until recently, the department was focused on stopping individual benefit fraud and investigated people who were flagged as being suspicious at job centers. However, it’s the large-scale efforts by criminal gangs that contributes the bulk of the issue. By deploying AI, billions of items of data can be quickly reviewed, fake identity cloning techniques commonly used by fraudsters are detected and the claim payments can be stopped.

Artificial intelligence algorithms are also used to scour social media accounts to uncover inconsistencies in the stories people tell on social media and the claims they are making for benefits. Lavish holiday parties are a red flag if you’re claiming unemployment benefits. Going on a cross-country race is not congruent with someone who receives disability benefits. If you claim single status and you post pictures of your wedding or spouse, it’s suspicious to the AI algorithms.

Reported Results

"AI identifies possible issues faster than human investigators who in the past would have to assess every claim."

Technology

"The algorithms look for patterns in claims such as the same phone number or applications written in the same style. 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 scour social media accounts to uncover inconsistencies in the stories people tell on social media and the claims they are making for benefits."

Function

Finance

Audit

Background

"Investment in data strategy, technologies that support machine learning and artificial intelligence, and hiring skilled data professionals is a top priority for the UK government.

Benefit fraud at the hands of criminal gangs cost the Department of Work and Pensions nearly £2.1 billion in 2016, a rise of £200 million in just one year. The losses to fraud equate to the entire budget of the Foreign Office, which is £1.1 billion annually."

Benefits

Data

Claims applications and social media posts, photos and other data