ZestyAI, a California-based InsurTech company leveraging artificial intelligence to assess climate and property risk, has revealed that over 12.6m homes in the U.S. are at high risk of hail-related roof damage, representing $189.5bn in potential replacement costs.
The data, powered by ZestyAI’s proprietary Z-HAIL™ model, underscores the financial impact of severe convective storms (SCS) and the growing necessity for more advanced and property-specific risk assessment tools in the insurance industry, according to InsurTech Insights.
Founded to bring AI-driven precision to risk modeling, ZestyAI combines aerial imagery, structural data, and local weather patterns through machine learning.
Its Z-HAIL model delivers granular insights at the individual property level, moving beyond traditional catastrophe models that focus only on portfolio-wide exposure.
This distinction is critical as traditional models often fail to capture the real-world drivers of hail damage—factors such as roofing material, age, and local environmental context.
ZestyAI’s new data highlights that severe hailstorms, part of the broader SCS category which also includes tornadoes and high-wind events, are becoming increasingly expensive.
In 2024 alone, such storms caused an estimated $56bn in damages, overtaking even hurricanes in total losses. Yet despite the mounting costs, many insurers continue to rely on outdated models not built for today’s hyper-localized climate threats.
The company aims to help insurers transition toward smarter underwriting and pricing models with tools like Z-HAIL.
The model has already proven its precision in real-world cases, such as a storm in Allen, Texas, where 2.5-inch hailstones struck. Among 483 insured properties analyzed by Z-HAIL, none rated as “Very Low” risk sustained damage, even though they sat adjacent to homes with significant losses.
Currently approved for use in 14 U.S. states—including the five with the highest exposure: Texas ($68bn), Colorado ($16.7bn), Illinois ($10.8bn), North Carolina ($10.4bn), and Missouri ($9.5bn)—Z-HAIL is undergoing further regulatory reviews as demand rises for climate-resilient underwriting strategies. States with the least exposure include Maine, Idaho, New Hampshire, Nevada, and Vermont.
“Catastrophe models have helped insurers understand where storms may strike and how losses might add up at a portfolio level,” said Kumar Dhuvur, Co-Founder and Chief Product Officer at ZestyAI. “But they weren’t built to assess risk at the individual property level… By analyzing the interaction between structure-specific features and local storm patterns, we can distinguish risk between neighbouring properties—enabling smarter underwriting, more precise pricing, and better protection for policyholders.”
Copyright © 2025 InsurTech Analyst
