The approved models—Z-HAIL™, Z-WIND™, and Z-STORM™—are designed to enhance underwriting and rating accuracy by offering precise assessments of risk for individual structures, a notable improvement over traditional ZIP code-based methods.
The decision comes amid a backdrop of increasing weather volatility across Arizona. In 2024 alone, the state experienced 67 days of severe weather, including high winds, large hail, tornadoes, and damaging downbursts, according to NOAA. These intense, localized wind events—particularly downbursts—often exceed 100 mph and have proven to be a leading cause of property damage, especially to roofs and vulnerable structures.
ZestyAI’s storm models aim to address the growing need for more granular risk assessment. By analyzing how localized climatology interacts with unique building characteristics, the models provide predictive insights into both the likelihood and severity of storm-related claims. The models are trained on extensive real-world claims data and have been validated to support accurate, transparent, and regulatory-aligned underwriting decisions.
Z-HAIL focuses on predicting hail damage risk using property-specific factors such as roof complexity, historical losses, and accumulated damage. Z-WIND leverages AI-powered 3D analysis of a property’s roof condition and structural vulnerabilities, combined with regional climate data, to assess wind-related risk. Z-STORM provides a comprehensive view of storm damage potential, modeling both frequency and severity by evaluating the interaction of weather conditions with structural features.
Bryan Rehor, Director of Regulatory Affairs at ZestyAI, emphasized the significance of the approval, stating, “Arizona is a key market for many of our carrier partners and one of the most rigorous regulatory environments for model review. This approval is a strong signal of confidence in our technology and our commitment to transparency, precision, and regulatory alignment.”
Arizona is now the 19th state to approve ZestyAI’s Severe Convective Storm suite and the fourth to approve a ZestyAI model overall. The company’s wildfire risk model, Z-FIRE™, is already in use throughout the state. With mounting climate-related risks across multiple perils, Arizona’s adoption of ZestyAI’s suite demonstrates a growing regulatory embrace of AI-powered tools that offer more accurate risk alignment, enable smarter underwriting, and support stronger resilience in the face of extreme weather.