ZestyAI, a Risk Decision Platform serving the insurance industry, has had its Z-WATER model for non-weather water risk accepted for use in carrier rate and rule filings across more than 20 US states.
Nevada, Oregon, Ohio, South Carolina and Oklahoma are among the jurisdictions to have granted approval most recently.
The regulatory clearances mean carriers can now use Z-WATER to assess non-weather water exposure at the level of an individual property, rather than relying solely on broader rating factors. According to the company, the model provides 18 times sharper risk differentiation than conventional approaches based on territory and property age.
Non-weather water damage has emerged as the fourth most expensive peril within homeowners insurance, generating in excess of $15bn in losses annually and touching more than a million claims a year, it said.
The average cost of these claims has also climbed by 80%, adding further strain to insurers’ loss ratios. Unlike storm or catastrophe-driven damage, this category of loss typically stems from everyday causes such as a burst pipe, ageing plumbing, a faulty appliance or a concealed leak, and can escalate significantly before it is noticed.
Insurers have long struggled to identify which specific homes carry the greatest exposure to this type of loss. Conventional rating methods, which lean on wide geographic zones and the age of a property, can fail to capture important distinctions between houses that otherwise appear similar.
Z-WATER is designed to close this gap. Built and tested against insurer claims data, the model applies computer vision to aerial imagery and combines this with property attributes, permit records, local climate patterns and surrounding infrastructure to gauge both the likelihood and potential severity of a non-weather water claim.
ZestyAI senior director of regulatory and government affairs Bryan Rehor said, “Non-weather water losses place real pressure on carriers’ books, but they’re also highly preventable when you understand where the risks actually lie. The growing regulatory acceptance of Z-WATER reflects a broader shift toward models that can identify meaningful differences in risk from one home to the next while providing the transparency regulators expect.”
Copyright © 2026 FinTech Global
