UK Government Aims to Tackle Insurance Fraud with AI

Tackle Insurance Fraud with AI

A bodybuilder, a cyclist and a student.

They didn’t walk into a bar. But they did raise some hair-raising fraudulent insurance claims.

In 2017, a cyclist claimed £135,000 compensation after he falsely stated that he fell off his bike following a collision with a pothole. A bodybuilder claimed £150,000 for a back injury that wasn’t hindering him from the press-up challenge he went on to film. And a student thought his luck was in when he tried to claim £14,000 for the “loss” of some of his more expensive personal items while on a jolly holiday in Venice.

Insurance fraud cases cost the U.K. billions of pounds every year. On average, it boils down to over £10,000 per fraudulent claim — and results in consumers having to spend an extra £50 per policy.

To drive these numbers down, Intelligent Voice, Strenuus and the University of East London are creating an AI and voice recognition technology that will help identify fraudulent claims.

Tackling the Big Issues

Insurance Companies currently face two major challenges.

The first is the large number of calls they receive for fraudulent claims. The second is adapting to the recent GDPR law, which prohibits so-called black box policies. Instead, insurance companies have to be able to explain to their customers, as well as regulators, how decisions have been made.

In response, London-based Intelligent Voice has set out to develop a set of Machine Learning algorithms that can identify fraudulent behavior in real time. The goal is to make processes more efficient and effective, as well as reduce the fatigue experienced by call agents.

The team has shown that they can match human-level efforts in identifying potential fraud.Intelligent Voice combines its machine learning and speech recognition skills with behavioral analytics knowledge from Strenuus, also based in London. The University of East London is working on adding an explainability layer to the technology that will determine how and when decisions were made in a particular case.

Their efforts are part of the U.K. government’s Next Generation Services Industrial Strategy Challenge Fund. The project will run for about two-and-a-half years.

Detecting Fraud Before the Payout

During calls to insurers, the system picks up signals of potential deception. These can take the form of specific words or phrases as well as tone of voice. A long short-term memory (LSTM) network has been trained to recognize the signals in real time, so call agents can respond to alerts immediately and change their responses accordingly.

Employee productivity gets a boost because calls flagged by the technology can be provided as a list noting potentially fraudulent markers. Call agents can jump directly to flagged sections for review.

Intelligent Voice’s machine learning algorithms are trained using hundreds of thousands of insurance calls, which have already been manually screened. To power this training, they use an assortment of NVIDIA GPUs and, in production, their software runs on NVIDIA Tensor Core V100 GPUs.

“From a technology perspective, we’ve not found anything which gives us the flexibility and performance that NVIDIA GPUs do,” said Nigel Cannings, CTO of Intelligent Voice. “The flexibility that CUDA offers, in particular, both on the programming side as well as supporting deep learning simultaneously, means that NVIDIA is the obvious choice for us.”

Source: NVIDIA Blog

Kayla Matthews

Higher-Ups More Likely to Break Policy, Data Breach Survey Finds

Data Protection Policies In an ideal scenario, the people at the highest levels of an organization would be the most likely to abide by data ...
Employees Digital

A Winning Data Strategy Series Part 1: Off to a Faulty Start

A Winning Data Strategy Series This is the first piece of a 5-part series on plugging the obvious but overlooked gaps in achieving digital success ...
Juan Pablo Perez Etchegoyen

7 Security and Compliance Considerations for Cloud-Based Business Applications  

Security and Compliance Considerations There’s no doubt on-premises deployments of mission-critical business applications provide more control over data as it resides within the four walls ...
Patrick Joggerst

Living on the Edge: The New Real-Time Communications Security Risks

Real-time communications Security Risks As more and more people have been forced to work remotely due to the global public health crisis, collaboration platforms have ...
Chandani Patel Volansys

Pillars of AWS Well-Architected Framework

Well-Architected Framework Cloud computing is proliferating each passing year denoting that there are plenty of opportunities. Creating a cloud solution calls for a strong architecture ...
Kaylamatthews

How AI Can Keep Documents Secure During the Age of Remote Work

Keeping Documents Secure While remote In response to the COVID-19 pandemic, global businesses have restructured operations to accommodate remote work and telecommuting. Humanity has collectively ...