• KTP between Domestic & General and Aston University will push boundaries of AI to develop an intelligent insurance fraud detection system
• Fewer fraudulent claims will lead to lower premiums
• Fraudulent claims in the UK in 2022 were valued at £1.1bn.

A partnership between Aston University’s Sir Peter Rigby Digital Futures Institute and Domestic & General, a global insurance and household appliance repair provider, will develop an insurance fraud detection system that uses generative artificial intelligence (AI).

Although certain fraud detection techniques – such as identity verification and fraud databases – are already available to insurance companies, there is no off-the-shelf technology that can integrate these and make them fit for purpose for D&G’s particular needs.

Fraud is an issue within the insurance sector. According to the Association of British Insurers, 72,600 dishonest claims were detected in 2022, with an overall value of £1.1bn. While the majority of claims made to D&G are genuine, the company does encounter a small but concerning percentage of fraudulent claims. Currently, D&G operates a fraud detection system that is only partially automated, and the company is exploring enhanced technologies to further strengthen its defences against such fraudulent activity.

An intelligent AI-powered insurance fraud detection system that can identify high-risk behaviours and patterns and enable the early detection of potentially fraudulent activity would transform D&G’s approach to insurance fraud. It would lead to a reduction in claims costs, allowing D&G to pass these savings back to its customers.

The project will need to overcome many technical challenges to create an efficient and user-friendly system at D&G that can detect and prevent fraud. This will be achieved by drawing on the latest AI techniques in development at Aston University, including natural language processing to analyse text and voice patterns, and artificial neural networks capable of extracting and learning from complex data.

This will create a system that can assign a risk score for each customer by analysing data held in different formats and different repositories, such as written emails and audio recordings of calls. The system will also be able to automatically analyse insurance accounts to identify potential duplication in customer and appliance details and types of claims - a common tactic used in fraud - and flag these to D&G’s fraud team.

Professor Abdul Sadka, director of The Sir Peter Rigby Digital Futures Institute at Aston University, said:

“This KTP offers a really exciting challenge, involving novel sources of data and uses of AI. We’ll be drawing together a suite of tools and techniques and integrating those to create an end-to-end system, which will be bespoke to Domestic & General but also pushes the boundaries of what’s currently possible in this field.”

Vipul Chhabra, chief underwriting and data officer at Domestic & General, said:

“Aston’s reputation, leading role in KTPs in the UK and the wide variety of their successful past products really impressed us. The potential for data to drive improvements right across our business is extensive and Aston is at the cutting edge of what’s possible in the field; combining that with our commercial knowledge makes for a really strong partnership.”

Professor Sadka, who leads the KTP, is a renowned expert on AI-powered multimodal data analytics, with a distinguished record in AI-enabled knowledge discovery. He will be joined from Aston University by Dr Amal Htait, lecturer in the School of Computer Science and Digital Technologies, who has extensive knowledge in information retrieval, machine learning, deep learning and the application of large language models.

Knowledge Transfer Partnerships, funded by Innovate UK, are collaborations between a business, a university and a highly qualified research associate. The UK-wide programme helps businesses to improve their competitiveness and productivity through the better use of knowledge, technology and skills. Aston University is a sector-leading KTP provider, ranked first for project quality, and second for the volume of active projects.