Experts at Allianz UK have collaborated on a new machine-learning tool designed to combat growing fraudulent claims.
The ‘Incognito’ tool was developed as part of a broader fraud prevention strategy, according to a news release by Allianz. It works by flagging potentially fraudulent claims that are then referred to fraud experts for review and investigation.
Fraud claims identified through Incognito have led to savings of £1.7 million to date, Allianz revealed. An additional £3.4 million is also being held in claim reserves pending the conclusion of ongoing probes.
“Our internal drive at Allianz has always been to put our customers front and centre,” said James Burge, head of counter-fraud at Allianz Commercial. “The development of ‘Incognito’ has ensured that we enhance the market-leading service that we provide to our customers. We have been able to settle claims quicker and identify fraud at the earliest opportunity.”
Allianz has been boosting its fraud prevention measures as insurance fraudsters become more sophisticated in their methods.
According to Allianz, application fraud savings have surged by 150% compared to year-to-date expectations, fuelled by the economic downturn, a fragile economy, and the ongoing cost-of-living crisis.
A recent noteworthy case involved a high-value claim related to storm damage to a property, resulting in a six-figure sum in savings.
The fraud detection team has also flagged high-value cases in motor and casualty claims, with Incognito identifying a contrived accident claim that saved £21,000. Another case involving a stolen vehicle is currently being investigated.
“The success of Incognito is shown through its cost-saving approach, consistent fraud detection rate over time, automation capabilities, and regulatory compliance,” said Alex Sorrie, head of claims data. “Our partnership-driven approach and use of technology has set a new blueprint for combatting fraud and protecting our genuine customers and their premiums.”
What are your thoughts on this story? Feel free to comment below.
