Brit, a UK-based specialty insurer and re-insurer, has launched a machine-learning algorithm that helps speed up identification of post-catastrophe property damage using ultra-high-resolution imagery.
The firm’s claims team used this algorithm to improve claims service and speed up payments to customers in the wake of Hurricane Ida.
Go deeper with GlobalData
The new machine-learning algorithm, which is developed by Brit’s data science team, uses ultra-high-resolution aerial images and data for evaluating the damage.
Brit claimed that the algorithm helps to pinpoint colour-codes, and displays properties by damage classification within days following a catastrophe event.’
This allows the claims team to identify, triage and assign response activity even prior to reporting of the claims.
The firm has been working in collaboration with GIC (Geospatial Insurance Consortium) since April 2019.
GIC, a non-profit entity, captures post-catastrophe ariel images for first responders and insurance firms.
Equipped with the GIC images and machine learning algorithm, the claims team with an adjusting platform can speed up claims payments in locations that cannot be serviced immediately by local field adjusters in the initial days after a catastrophe.
Brit group head of claims and operations Sheel Sawhney said: “A claim is the single most important interaction that an end client will have with their insurer and this will often be at a time of significant difficulty. Innovation and technology are critical to the equation.
“This use of machine learning techniques and the best available imagery is further evidence of how our award-winning claims team is finding new ways to increase the speed and accuracy of claims payments.”
Earlier this week, US-based Farmers Insurance announced plans to use robots for in-field catastrophe claims handling and non-catastrophe property inspections.
Called Spot, the robot was developed by Boston Dynamics and customised for the insurer.
