Resources

ZestyAI today announced a new partnership with Kin Insurance, a direct-to-consumer, digital home insurance provider committed to serving catastrophe-exposed markets.

As part of its expansion into California, Kin has deployed Z-FIRE, ZestyAI’s wildfire risk model, to accurately assess property-level wildfire exposure and expand access to coverage in high-risk areas.

The model was integrated in just 10 days, enabling Kin to move quickly in meeting the needs of California’s evolving market.

Meeting California’s Growing Need for Property-Level Wildfire Insight

California continues to face a widening insurance gap, driven by more frequent natural disasters and insurer withdrawals.

This partnership supports Kin’s commitment to bringing insurance options back to communities impacted by limited availability of coverage.

Z-FIRE uses machine learning to evaluate each property’s unique characteristics, including defensible space, building materials, topography, vegetation, and more, to predict which properties are most likely to experience a wildfire and which ones will survive.

Why Kin Chose Z-FIRE to Support Responsible Growth

Michael McCright, vice president, pricing and risk management at Kin, said:

“California requires a smarter, more modern approach to home insurance risk management. ZestyAI’s Z-FIRE model brings the level of insight we need to confidently assess risk and offer coverage in areas at risk of wildfire.”

“Kin’s expansion into California is exactly the kind of forward-thinking move our technology was built to support,” said Attila Toth, Founder and CEO of ZestyAI. “Together, we’re helping show that with the right data and tools, insurers can re-enter challenging markets with confidence—and deliver meaningful protection to homeowners who need it most.”

“Equally important, Z-FIRE empowers insurers to recognize and reward mitigation efforts at the property level, encouraging homeowners to take action that reduces risk for themselves and their communities.”

Real-World Performance: Z-FIRE in the Los Angeles Wildfires

Z-FIRE’s performance has been validated through real-world events: Following the recent Los Angeles wildfires, Z-FIRE’s highest-risk ratings closely corresponded with the hardest-hit areas, with 94% and 87% of the areas affected by the Palisades and Eaton fires rated as High Risk by the model.

Among homes located within these perimeters, those flagged as having the highest vulnerability to damage were 50% more likely to be destroyed—highlighting the critical value of property-specific insights, even in dense urban settings.

ZestyAI works closely with regulators to ensure transparency, validation, and continuous monitoring of its AI-driven models.

The company has secured regulatory approvals across all Western states for Z-FIRE, along with broad acceptance of its severe convective storm suite of models in Texas, Colorado, the Midwest, and the Great Plains.

The Michigan Department of Insurance and Financial Services has approved ZestyAI's Severe Convective Storm suite, including the proprietary Z-HAIL™, Z-WIND™, and Z-STORM™ models.

Michigan Faces Rising Losses From Severe Convective Storms

The approval comes as Michigan contends with rising weather-related insurance losses.

According to NOAA’s National Centers for Environmental Information (NCEI), the state has experienced over $5 billion in insured storm damage since 2019, with hail and straight-line winds accounting for the majority of claims. In 2024, a series of intense summer storms alone caused more than $1.2 billion in insured losses.

Why Carriers Need Property-Level Precision

ZestyAI’s AI-driven platform predicts the likelihood and severity of claims from severe convective storms at the individual property level by analyzing the interaction of local climatology with property-specific characteristics. In contrast, most risk assessment models today rely on broader territory or ZIP code-level evaluations, overlooking critical property-level factors. 

Each model is built and validated on extensive real-world claims data and delivers transparent explanations of the key drivers behind every risk score, helping carriers make more accurate underwriting and rating decisions.

How ZestyAI’s Storm Models Improve Risk Assessment

Key capabilities include:

• Z-HAIL: Predicts hail damage risk and claim severity using property-specific attributes like roof complexity, historical losses, and accumulated damage, identifying which homes are most likely to file a claim, even within the same neighborhood. 
• Z-WIND: Combines AI-generated 3D analysis of roof condition, complexity, and potential failure points with local climatology to deliver pivotal insights into property-specific wind vulnerability and severity. 
• Z-STORM: Predicts the frequency and severity of storm damage claims, including hail and wind, examining the interaction between climatology and the unique characteristics of every structure and roof.

What Michigan’s Approval Means for Insurers

“As severe weather becomes more frequent and costly, insurers need tools that keep pace with evolving risks,” said Bryan Rehor, Director of Regulatory Affairs at ZestyAI.

“This approval gives Michigan carriers access to precise, property-level insights that support smarter underwriting and help reduce preventable losses.”

Michigan's approval marks the 17th state to embrace ZestyAI's Severe Convective Storm suite, reflecting increasing regulatory confidence in AI-powered risk models that deliver actionable insights while supporting industry-wide resilience efforts.

With insured losses projected to exceed $30 billion, the recent Los Angeles wildfires rank among the costliest in U.S. history—reshaping how insurers think about risk, resilience, and readiness.

Watch the Full Webinar → LA Fires in Focus: What Insurers Need to Know

In this on-demand webinar, experts from the Insurance Institute for Business & Home Safety (IBHS), the Western Fire Chiefs Association, Cal Poly’s WUI Fire Institute, and ZestyAI unpack what really happened—from frontline response to lab-based research and model performance—and share critical strategies insurers can use to prepare for what’s next.

Watch this session if you’re a Product Managers, Underwriters, Actuaries, and Risk & Innovation leaders looking to make informed decisions in an increasingly volatile wildfire landscape.

What You’ll Learn

• Key takeaways from the Los Angeles wildfires
• Research on structure-to-structure fire spread and resilience factors
• How wildfire risk models performed—what we got right (and wrong)
• Practical strategies to reduce exposure and strengthen resilience

Meet the Experts

• Anne Cope, Chief Engineer, IBHS
• Bob Roper, CEO, Western Fire Chiefs Association
• Frank Frievalt, Director, WUI Fire Institute at Cal Poly
• Kumar Duhvur, Co-Founder & CPO, ZestyAI

ZestyAI today announced that the Connecticut Insurance Department (CID) has formally approved its Roof Quality solution for use in residential property underwriting.

CID conducted a comprehensive third-party actuarial review of ZestyAI’s model, evaluating methodology, data integrity, and regulatory compliance against its rigorous standards.

What CID’s Approval Means for Carriers

Part of Z-PROPERTY™ , the Roof Quality model enables insurers to assess and price roof risk with unmatched accuracy.

By combining 3D property analysis, high-resolution aerial imagery, and AI trained on extensive real-world data, the platform replaces subjective or incomplete assessments with objective, property-specific intelligence.

The model classifies roofs into five standardized condition levels, helping insurers assess property risk with greater precision. It distinguishes between surface-level wear and structural issues, flagging meaningful signs of deterioration such as missing shingles, tarps, or water pooling.

Bryan Rehor, Director of Regulatory Affairs at ZestyAI, said:

“Roof condition is one of the strongest predictors of loss, yet historically one of the hardest to assess without costly inspections. This approval affirms the accuracy, fairness, and transparency of our approach and reflects our broader commitment to aligning innovation with consumer protection.”

How ZestyAI’s Roof Quality Model Improves Risk Assessment

ZestyAI maintains active engagement with the National Association of Insurance Commissioners (NAIC) and state-level departments to ensure its models meet evolving standards for fairness, transparency, and consumer protection.

By proactively filing through in-house Rating and Advisory Organizations, ZestyAI ensures its models meet the strictest regulatory standards before reaching the market. 

ZestyAI’s models are trusted by regulators and insurers to assess risk in the nation’s most climate-exposed regions with Z-FIRE, ZestyAI’s wildfire risk model, approved by regulators in all western states. Its Severe Convective Storm suite is approved in 16 states across the Midwest, Great Plains, and South.

ZestyAI today announced a new partnership with Farmers and Mechanics Mutual Insurance Company of West Virginia (FMIWV) to strengthen underwriting accuracy and improve risk-based pricing.

Why Accurate Roof Data Matters More Than Ever

Roof claims are the leading driver of insurance losses, yet many carriers still depend on self-reported data, which can be unreliable, or physical inspections, which are costly and hard to scale. Recent research shows that 15% of roofs are at least eight years older than reported, highlighting the need for more reliable, data-driven alternatives.

To address long-standing challenges in accessing reliable property insights, FMIWV selected Z-PROPERTY™.

Why FMIWV Chose Z-PROPERTY

Dan Otto, Senior Vice President and Chief Financial Officer at FMIWV, said:

"After evaluating several options in recent years, we chose ZestyAI based on their strong coverage and ease of implementation. Getting started using the technology was easy. We’re particularly focused on using their property insights to provide additional underwriting information for new business and renewals.”

ZestyAI’s advanced insights help FMIWV:

• Identify high-risk properties early to prioritize mitigation and prevent losses
• Enhance risk selection and pricing precision with objective, property-level data
• Reduce inspection costs and turnaround time by minimizing the need for on-site assessments
• Streamline straight-through processing for low-risk properties to improve efficiency and speed to bind
• Reduce premium leakage by aligning pricing with actual exposure

“FMIWV is showing how regional carriers can lead with data-driven underwriting that improves operations and elevates the customer experience,” said Attila Toth, Founder and CEO of ZestyAI.

“By grounding decisions in reliable, property-level data, they’re improving efficiency, reducing risk, and raising the bar for underwriting and rating precision.”

Wildfire Risk Is Rising Nationwide‍

Wildfire seasons are getting longer, more destructive, and harder to predict—and they’re no longer just a Western U.S. concern. From the Southeast to the Midwest, wildfire risk is emerging in places many insurers haven’t traditionally watched.

What the Latest Data Reveals About Wildfire Exposure

Drawing from the latest national datasets and insights from ZestyAI’s Z-FIRE™ model, this visual guide to wildfire risk in the U.S. shows:

• New wildfire hotspots: Discover where risk is rising fastest.
• Mitigation gaps: Learn how a lack of defensible space is putting thousands of homes in danger across the country.
• Top risk drivers: See how features like overhanging trees and wooden roofs are fueling destruction in high-risk areas.

Download Free Infographic

BONUS: You’ll also get access to our latest online event with IBHS and Western Fire Chiefs Association, The LA Fires in Focus: What Worked, What Didn’t, What’s Next for Insurers.