Case Study

Unlocking telematics data with Aioi Nissay Dowa Europe

Discover patterns in customers behaviour to reduce risk, lower premiums for good drivers, and promote safer driving habits that benefit everyone.





off-policy trips detected in first 30 days.


policyholders using personal vehicles for commercial deliveries.


model accuracy.


In order to assess the level of risk that a current or potential customer represents to an insurer, a deep and data-driven understanding of their behaviour is essential. Traditionally, insurance firms would rely on statistical averages to quote customers. As roads get busier and the market gets even more competitive, insurers need more effective techniques for understanding driving behaviour.

Aioi Nissay Dowa Europe (AND-E) is constantly looking for ways to encourage safer driving patterns to their customers through a merit-based reward scheme and offering safer drivers with cheaper policies upon renewal. They needed a way to automatically detect safe patterns of driving from those that could be deemed dangerous, or outside of the terms of a customer’s policy.


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.


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.

AND-E Logo-2

"This human-AI collaboration improves the efficiency of human resource allocation, compared to manual searching alone, freeing up valuable resource. By identifying drivers using their vehicle for deliveries, we can encourage customers to arrange appropriate cover, helping to ensure that in the event of an accident they are able to claim and protect anyone else involved in a collision."

Nika Lee
Chief Underwriting Officer

Contact us to learn more...


Deepen your knowledge

View Resources

5 min read
Why AI Governance Matters in the Fight against Insurance Fraud
Fraud is one of the most pervasive threats in the insurance industry. Insurance fraud is estimated to cost insurers £1.1 billion in the UK alone. As...
4 min read
7 Steps for Scaling AI Governance in Insurance Pricing
The complexity of modern pricing models, coupled with the regulatory changes that are due to come into effect this year, means that insurers need to...
4 min read
Aioi R&D Lab - Oxford in 2024
One year into its mission to solve global-scale societal issues through the creation of products and services powered by AI technologies, the Aioi...

Stay connected

News, announcements, and blogs about AI in high-stakes applications.