Zurich & UTS AI partnership transforms underwriting process

Zurich Financial Services Australia (Zurich) has concluded the first phase of its collaboration with the University of Technology Sydney (UTS) to develop Artificial Intelligence (AI) models aimed at enhancing the underwriting process for life insurance applications, particularly those involving mental health disclosures.

The partnership, which involved more than six months of collaboration with UTS Rapido, a research and development hub at the university, has produced AI models capable of making immediate underwriting decisions without requiring doctor’s reports. Previously, underwriting decisions could take up to 22 days when mental health disclosures were involved.

According to Jacqui Lennon, Head of Retail at Zurich Australia & New Zealand, the utilisation of AI models in the underwriting process will significantly reduce the need to obtain doctor’s reports. "By using AI models to assist the underwriting process, Zurich can eliminate significant friction within the application process and reduce applicant concerns around privacy," Lennon stated.

The AI models were developed using anonymised data from seven years of past applications and identified several factors correlated with a mental health exclusion on an applicant. These factors include lack of participation in sports or recreational activities, the occurrence of chronic health issues beyond mental health, time spent in hospital or undergoing medical treatment in the past five years, and having close biological relatives with health conditions such as diabetes, cancer, or heart disease.

Currently, around 25% of the life insurance applications Zurich receives include a mental health condition disclosure. In 2023, mental health emerged as the third most common cause for claim at Zurich, accounting for 20% of all claims and resulting in AUD $255 million in claims payments. For some of Zurich’s retail life insurance products, mental health is one of the leading reasons for claim, accounting for up to 35% in some cases.

John Kim, Chief Data Officer at Zurich Australia & New Zealand, emphasised the benefits of utilising AI in underwriting. "Using AI allows Zurich to analyse thousands of data points, which would not be possible for a human to do," Kim said. "This project is a key step in Zurich’s journey to being Australia’s leading digital insurer, and it allows us to provide protection to more Australians when they need it most."

Beyond underwriting, Lennon noted that the AI models’ findings will guide the ongoing delivery and evolution of Zurich’s preventative health and wellness offerings. "In future, these models could potentially be used to analyse and improve the underwriting of conditions beyond mental health, such as cancer, cardiovascular, or musculoskeletal conditions," Lennon added, contingent on prevailing data.

The AI models will support the verification of underwriting decisions made by Zurich’s team and the existing rules engines in use. This approach is in line with Zurich’s AI philosophy to ‘always keep a human in the loop’ to maintain a balance between technological advancements and human oversight.