Dispute resolution law firm Kennedys and the University of Manchester will develop next-generation fraud prevention software for the benefit of insurers.
“With assistance from the University, the two-year project will see us combine our existing fraud expertise and international data sets to develop machine learning techniques,” announced Kennedys. “We will then pass these on to help our global insurer clients to better detect and manage fraud.”
The academic team from the University of Manchester consists of Decision and Cognitive Sciences Research Centre (DCSRC) director Jian-Bo Yang and professor of decision science and support systems Dong Ling Xu.
“We are confident that we can help Kennedys improve its current system,” commented Yang, who also serves as professor of decision and system sciences. “The key is to try and develop a hybrid system where you can use both big data and human knowledge in deep learning to tackle the problem, which we call transparent machine learning.
“In this way you can explain exactly why you reach your decisions. It is evidence-based, transparent decision-making.”
Funding for the collaboration has been secured from the Innovate UK Knowledge Transfer Partnership. The amount of monetary support was not disclosed.
“This latest development is part of our overall strategy to develop an insurance legal services platform that covers the lifecycle of a claim from inception to settlement,” said project director and Kennedys head of research and development Karim Derrick. “At the heart of that platform is data.
“We are combining our legal expertise, our toolkit products, our aggregated data and now cognitive computing expertise from a world-leading university to deliver a business service that is much greater than the sum of its parts.”
Related stories:
CUE database expands to include travel insurance claims
LV= to reveal data on insurance fraudsters
