Unlocking telematics data with Aioi Nissay Dowa Europe

Solution:

Mind Foundry worked closely with domain experts at AND-E to maximise the value they get from their telematic data. Together, using the Mind Foundry Platform, we developed a customised, fully automatic, end-to-end pipeline to separate out the safest drivers from those who engaged in risky driving behaviour, off-policy behaviour (such as using their personal coverage for commercial delivery driving), or activities designed to conceal or distort true behaviour.

The solution was built to be explainable and collaborative, by design. It included different levels of granularity at multiple stages so that it could not only flag which “trips” on a policy were safe or unsafe, but also which moment or moments in the trip were most influential in shaping this conclusion.

As AND-E investigated, confirmed, or corrected each flag, the model improved itself using a Continuous Metalearning capability. It integrated data back into the solution to effectively govern new risks, while enabling the model to learn new types of “trips” in production, meaning no manual retraining is needed to continuously adapt, optimise operations, and learn with AI.

Results:

The solution enabled AND-E to prioritise investigations of specific trips or policies based on risk and use this information to notify customers, reduce liability, and improve claims outcomes. This resulted in:

• Mind Foundry’s solution reached a precision of 99.4%, validated by domain experts at AND-E.

• 40,000 off-policy delivery trips discovered in the first 30 days.

• 100 policyholders discovered using their vehicle for delivery at least 50% of the time during that period.

The model has enabled AND-E to extract more value from their data to further advance their business processes and gain a better understanding of their customers' needs.