Subrogation opportunities are difficult to identify at scale, and personal injury protection (PIP) claims are even more complex. The criteria involved is often hard to verify, making these exposures particularly challenging to uncover with traditional methods. Manual reviews are resource-intensive, while conventional text analysis tends to overlook valuable opportunities. As a result, insurers are turning to AI-powered detection to solve these challenges.
To illustrate, consider this example shared by Benjamin Wonderlin from our Data Science team. In this case, we assisted a leading US P&C insurer by identifying a subrogation opportunity in New York, a state where recovering on PIP claims is notably challenging due to stringent legal criteria. These criteria include the requirement for one of the involved vehicles to be a commercial livery vehicle or exceed 6,500 lbs. in weight, which is difficult to verify at scale.
Using GenAI, Shift Subrogation analyzed available third-party vehicle information and compared it against external data sources. This process automatically identified the third-party vehicle as a registered rideshare, thereby meeting the potential for subrogation criteria. The claim then entered Shift’s detection pipeline, where AI models read the associated notes and determined that the rideshare vehicle was also likely at fault for the accident.
By combining external data validation with intelligent text analysis, Shift generated a clear, actionable alert. This saved valuable time for claims handlers and also helped the insurer identify a recovery opportunity that could have gone undetected.
This video is part of a series of interesting cases presented by our insurance-focused team of data scientists. For more examples of Shift Technology's AI-driven results, browse the AI in Action library