OnePath continues to invest in and improve AI underwriting engine

OnePath continues to invest in and improve AI underwriting engine

Around 2,000 advisers currently using the risk engine

Credit: © Solarseven -

One of Australia’s largest life insurers OnePath is continuing to invest in its inhouse AI underwriting engine, making more than 70 enhancements since its official launch in November.

Around 2,000 advisers are now using the improved risk engine to research various conditions, OnePath said.

A key aim of the engine is to significantly reduce the number of questions it asks a particular customer segment when they apply for a policy.

To achieve this, OnePath partnered with the University of Technology Sydney’s (UTS) Advanced Analytics Institute (AAi) in 2016. UTS researchers worked with 10 years' worth of data extracted from three core systems (some "tens of millions of rows of data") and applied advanced analytics and machine learning techniques to make connections between customer cohorts, the questions and answers, and resulting claims.

The techniques have been used to slim down the huge number of questions asked in insurance application forms, and bring “plain English” to questions around medical conditions.

To date, almost 1,000 unique conditions (including aliases) have been selected from the engine’s catalogue, 900 of which are medical. Image testing, vertebral disc-related issues and muscular back pain have been the top three most selected medical conditions so far. Some 52 unique travel destinations and 41 unique pastimes have been searched for and served up by the engine, with the US, Indonesia and the UK the top three travel destination searches and skiing, dirt biking and diving the most common pastime searches. 

The number of advisers using the engine is set to increase in coming months, said OnePath chief underwriter Peter Tilocca.

“Close to 2,000 advisers have now used the risk engine to research conditions. With every enhancement we make there is an educational period that follows, so we expect this number to grow considerably over the next six months,” he said.

The enhancements have been well received by advisers so far, OnePath said, revealing a Net Promoter Score for the engine of 65. Over the next quarter, OnePath will continue to respond to adviser feedback on the engine, prioritising enhancements and inclusions based on this and claimant requests, the company said.

“Ongoing monitoring of feedback and the updating of the medical catalogue and aliases are crucial elements of maintaining a leading-edge underwriting engine,” said Tilocca.

“Our ability to monitor this feedback and respond to requests is only enhanced by our decision to develop this capability inhouse,” he added.

Previously an arm of ANZ bank, OnePath Life insurance was formally acquired by Zurich Australia in June. The business serves more than two million customers and pays more than $1 billion per annum in claims.

Join the CIO Australia group on LinkedIn. The group is open to CIOs, IT Directors, COOs, CTOs and senior IT managers.

Join the newsletter!


Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.

Tags financeAIinsurancemachine learningOnePath

More about AdvancedANZAustraliaTechnologyUniversity of Technology SydneyUTS

Show Comments