Brit Introduces A Machine Learning Algorithm To Accelerate Post-Catastrophe Claims Response

Brit, a London-based specialty insurer and reinsurer, announced the construction and successful proof-of-concept launch of a unique machine-learning algorithm that uses ultra-high-resolution photography to speed up the detection of post-catastrophe property damage.

In the aftermath of Hurricane Ida, the Brit claims team and its delegated claims adjusters use this proof of concept to improve claims service and accelerate payments for clients.

Brit’s Data Science team created and overlaid a machine-learning algorithm to access the ultra-high-resolution ariel photos and data in this innovation. Within days of a disaster, it locates, color-codes, and shows properties based on damage classification. This allows the claims team to identify, triage, and assign response action even before reported claims.

Brit has been a part of the Geospatial Insurance Consortium (GIC) since April 2019, a non-profit that captures best-in-class post-event ariel imagery for first responders and insurance firms. The Brit’s claim team has a virtual claims adjusting platform with GIC pictures and a machine learning algorithm that can speed claims payments in regions where local field adjusters cannot instantly respond in the days following a disaster.

A claim is the single most important interaction that an end client will have with their insurer, according to Sheel Sawhney (Group Head of Claims and Operations), and it will often be at a time of great difficulty. Hence, they are constantly working to improve service and the speed with which they can resolve customer issues. Technology and innovation are also essential components of the process.

Using this developed machine learning techniques and the best available imagery, Brit’s claims team finds an improved efficiency and accuracy of for processing claims payments.

Source: https://www.britinsurance.com/news/ml-innovation-in-claims

Other Source: https://www.insurancejournal.com/news/international/2021/09/21/633025.htm