ZestyAI, the leading provider of AI-powered property and climate risk analytics, today announced that its non-weather water risk model, Z-WATER™, has received approval in Wisconsin for use in underwriting and rating.
Non-weather water is one of the costliest and fastest-growing perils in homeowners insurance, now ranking as the fourth costliest peril overall, with claim severity up 80% over the past decade—surpassing hurricanes. These losses stem from everyday risks like burst pipes, appliance failures, and plumbing leaks. With average claim costs now exceeding $13,000, their financial impact rivals catastrophe events.
Z-WATER is built, tested, and validated with real insurer loss data, ensuring accuracy and regulatory credibility. The model uses computer vision to analyze aerial imagery alongside tax assessor data, permit records, climatology science, and infrastructure insights to assess key property-level risk factors. By modeling how these variables interact, Z-WATER predicts both the frequency and severity of non-weather water claims with up to 18x greater accuracy than traditional models.
With this approval, insurers in Wisconsin can begin using Z-WATER to:
- Set more accurate, property-specific rates
- Align coverage with actual home vulnerabilities
- Optimize inspections and mitigation strategies, such as the adoption of water sensors
- Reduce cross-subsidization and improve portfolio performance
“Non-weather water is one of the most frequent and expensive sources of loss for insurers, and it behaves differently than other perils,” said Bryan Rehor, Director of Regulatory Strategy at ZestyAI.
“Z-WATER captures the property-level features that truly drive risk—such as plumbing systems, home design, and even vegetation patterns, giving insurers a much clearer picture of where losses are likely to occur.
"This approval demonstrates that regulators recognize the value of AI models that are explainable, data-driven, and validated against real claims," he added.
This approval adds to ZestyAI’s growing regulatory momentum. Across five perils, including wildfire, hail, wind, storm, and now non-weather water, ZestyAI has secured more than 70 approvals coast-to-coast. In addition to these peril models, ZestyAI’s Z-PROPERTY™ solution has also earned nationwide approvals, giving insurers trusted roof and parcel-level insights with the same regulatory credibility.