Queen's University student has key to beating insurance fraud
A Queen's University student believes she has cracked the code of staying ahead of insurance fraudsters.
PhD student Jiawen Sun from Tianjin in China specialises in big data and has been working on the anti-fraud software for three years.
Her programme is designed to rapidly sift through large quantities of an organisation's data and detect insurance fraud.
"Organisations are collecting increasing amounts of data, which is usually represented by graphs and can be useful for detecting fraud," she explains.
"However, as data sets grow into the trillions of bytes and beyond, this creates problems in high-performance computing, making it very hard to use the computer at full capacity."
Her research was carried out at the Queen's School of Electronics, Electrical Engineering and Computer Science and the Institute of Electronics, Communications and Information Technologies (ECIT).
She has previously spoken of how after completing her undergraduate degree in China, her grandmother inspired her to pursue a scientific PhD abroad, and of how decoding big data can change the world.
"I am fascinated by this research in particular because it offers opportunities to improve or change many aspects of our daily lives," she told Soapbox Science last year.
"(This includes) predicting and managing climate and weather; detecting health issues of individuals and enabling timely treatment; and social network analytics."
Dr Hans Vandierendonck supervised the project and said her work could be "extremely valuable" in disrupting fraudsters.
"These techniques accelerate graph analytics up to ten-fold, which is a game-changer for many organisations, allowing them to tap into analysis that they have never used before and at a much faster pace."
He said Jiawen's work now outperforms many of the current state-of-the-art programmes.
Ms Sun recently received a Silver medal at a computing machinery student competition, sponsored by tech giants Microsoft.
It will be hoped her new innovation will go some way to reducing over £1bn in fraudulent insurance claims in the UK each year.
The Association of British Insurers (ABI) say that in 2016, insurers detected 125,000 dishonest insurance claims valued at £1.3bn.
The real figure is believed to be much higher, with a similar amount undetected each year.
At present, the insurance industry invests £200m a year to tackle fraud.
The offences can range from opportunists inventing or exaggerating claims to highly organised criminal gangs engaged in 'cash for crash' motor fraud scams.