AND-E and Mind Foundry forge powerful AI alliance to combat underinsurance in auto policies

This method relies on Bayesian inference within probabilistic machine learning. It was rigorously tested in a scenario involving drivers using private vehicles for commercial purposes. The approach accurately identified a high percentage of prioritised driver referrals erroneously covered only for social and domestic use.

The research report, titled “A Bayesian Approach for Prioritising Driving Behavior Investigations in Telematic Auto Insurance Policies,” underscores the potential of telematics data to pinpoint specific driving patterns. Data from black box telematics systems, including location, speed, acceleration, braking, fuel consumption, and idling time, offers valuable insights. These data are scrutinised for events and patterns that suggest vehicles might be used for deliveries.

By integrating machine learning, AND-E established a prioritised order for human investigation, enhancing resource allocation efficiency compared to manual searches alone.

Nika Lee, chief underwriting officer at AND-E, emphasised: “This new approach enables us to efficiently identify delivery drivers, allowing us to verify and take action before a risk materialises into a claim.”

With the UK’s significant presence of gig economy drivers, particularly in the delivery sector, which has recently grown, motor insurance providers like AND-E face mounting pressure to detect vehicles used outside policy terms. This helps mitigate loss costs and ensures motorists have appropriate coverage.

Lee cautioned that “the risk isn’t solely rooted in underinsured delivery drivers; reports indicate drivers face increasing workloads and staff shortages, elevating the risk of claims. Early detection of delivery driving is essential to safeguard customers and mitigate non-disclosure risks.”

The collaborative approach by AND-E and Mind Foundry represents a significant stride in addressing underinsurance. It offers a more efficient means of identifying commercial vehicle usage, ensuring proper coverage for motorists in case of accidents.