Reports & Research

The Silent Peril Reshaping Homeowners Insurance

Non-weather water damage rarely makes headlines, but it’s quietly eroding profitability across the country.
It is now the fourth costliest peril in homeowners insurance, and claim severity has increased 80% in the last decade—a trend that’s accelerating even as frequency remains relatively flat.

Traditional risk models struggle to capture the early warning signs behind these losses, leading to mispriced policies, undetected exposure, and rising volatility for carriers.

Want the full analysis? Download the complete “Winning the Fight Against Non-Weather Water Losses” guide.

Why Loss Severity Keeps Rising

Aging homes and overlooked system failures

Many of the most expensive losses stem from aging plumbing, deteriorating materials, and slow-burn failures that often go undetected until damage is significant.

Frequency is flat—severity is not

Loss patterns suggest that while the number of events hasn’t surged, the financial impact of each event has—a signal that traditional models are not capturing the right property-level predictors.

The Property Features Most Predictive of Water Losses

The overlooked attributes that traditional models miss

Standard territory- or age-based assessments often ignore the property-specific details that meaningfully influence water loss risk, including:

• supply line material and age
• plumbing configuration
• occupancy patterns
• system maintenance and upgrades
• moisture exposure and prior loss indicators

These factors vary widely between neighboring homes—yet most models treat them as identical.

Where Traditional Underwriting Falls Short

ZIP-code and age-based proxies mask true risk

Legacy approaches rely heavily on broad territory-level assumptions that overlook structural vulnerabilities and system conditions.

Limited visibility creates mispriced policies

Without property-level insight, high-risk homes are often underpriced while lower-risk homes subsidize them—driving loss ratio volatility over time.

Get deeper insights on the drivers of water loss severity in our full guide → “Winning the Fight Against Non-Weather Water Losses”

How AI and Property-Level Data Are Changing the Landscape

AI models trained on real-world claims data can identify early signals of potential water loss by analyzing the interaction between:

• plumbing systems
• property attributes
• historical patterns
• material degradation
• repair history

This enables carriers to segment risk accurately, adjust pricing, and reduce preventable losses—long before small issues turn into major claims.

What Homeowners Actually Understand About Water Risk

Misconceptions around coverage and prevention

ZestyAI’s research shows that many policyholders:

• misunderstand what is and isn’t covered
• underestimate how much damage water can cause
• rarely take preventive actions unless prompted

This disconnect creates an opportunity for carriers to strengthen education, mitigation, and customer engagement.

Steps Carriers Can Take Today

Improve segmentation and rating accuracy

Property-level signals enable more precise risk tiers and more stable long-term portfolios.

Strengthen mitigation and reduce loss severity

Insights help identify which homes are at elevated risk and where targeted mitigation can reduce exposure.

Enhance underwriting workflows with explainable insights

Transparent, explainable AI helps underwriters understand the key drivers behind elevated risk—supporting both decision-making and regulatory review.

Get the Full Guide

Our new research paper, Winning the Fight Against Non-Weather Water Losses, breaks down the trends reshaping this growing peril—and the strategies carriers can use to get ahead of it.

Access the Guide

ZestyAI's analysis revealed that more than 12.6 million U.S. properties are at high risk of hail-related roof damage, representing $189.5 billion in potential replacement costs.

Powered by ZestyAI’s Z-HAIL™ model, the analysis underscores the growing financial threat of severe convective storms (SCS), including hail, tornadoes, and wind events. In 2024 alone, damages from SCS were estimated at $56 billion—surpassing losses from hurricanes.

Yet many insurers still rely on traditional models designed to estimate portfolio-level exposure, not property-level risk. As hail events increase in severity and frequency, these models often miss the structural and environmental conditions that drive real losses.

Kumar Dhuvur, Co-Founder and Chief Product Officer at ZestyAI said:

“Catastrophe models have helped insurers understand where storms may strike and how losses might add up at a portfolio level. But they weren’t built to assess risk at the individual property level, and they often miss the specific conditions that drive hail damage. By analyzing the interaction between structure-specific features and local storm patterns, we can distinguish risk between neighboring properties—enabling smarter underwriting, more precise pricing, and better protection for policyholders.”

Z-HAIL evaluates hail risk using a proprietary blend of climate, aerial, and property-specific data. By applying advanced machine learning to these inputs, Z-HAIL delivers highly granular predictions that reflect both the physical characteristics of a structure and the storm activity in its immediate surroundings.

Key findings from the analysis:

• 12.6 million U.S. structures flagged as high risk for hail-related roof damage
• $189.5 billion in total potential roof replacement exposure

Top five states by dollar exposure:

• Texas ($68B)
• Colorado ($16.7B)
• Illinois ($10.8B)
• North Carolina ($10.4B)
• Missouri ($9.5B)

States with the lowest dollar exposure:

• Maine ($4.7M)
• Idaho ($12.8M)
• New Hampshire ($18.5M)
• Nevada ($49.3M)
• Vermont ($64.7M)

In recent case studies, Z-HAIL has demonstrated the ability to pinpoint which properties are most susceptible to hail damage—even within the same neighborhood and exposed to the same storm. In one example from Allen, Texas, following a storm with 2.5-inch hailstones, Z-HAIL segmented risk across 483 policies, identifying no losses among properties rated “Very Low” by the model. This level of intra-territory precision gives insurers the ability to refine risk selection with confidence—even in the most hail-prone regions of the country.

Severe convective storms are becoming more frequent and costly, putting pressure on insurers to refine underwriting and risk management strategies. 

On April 2, our experts covered:

• Key drivers behind increasing severe storm losses
• What La Niña means for the 2025 season
• How AI-powered risk models improve risk segmentation
• Live Q&A – Get expert answers to your toughest questions!

Missed the live event? Stream now! 

Severe convective storms (SCS)—including tornadoes, hail, and damaging wind events—resulted in $58 billion in insured losses across the U.S in 2024.

Insurers face a dual challenge: navigating the uncertainty of storm patterns while ensuring their portfolios remain resilient enough to absorb the financial strain from clustered, high-loss events.

Research with IBHS confirms that SCS damage accumulates over time, particularly affecting rooftops after multiple exposures to intense storm activity. As housing stock deteriorates, insurers must reassess their portfolios to ensure underwriting, rating, and loss cost controls align with their risk appetite and maintain premiums that accurately reflect evolving exposure.

Get ahead of rising storm risks with expert insights that help you strengthen underwriting, risk assessment, and claims management.

Get our new report.

A staggering $2.15 trillion worth of U.S. residential property is at high risk of wildfire damage, according to a new AI-powered analysis from ZestyAI, the leader in climate and property risk analytics. The study, which assessed 126 million properties nationwide, found that 4.3 million individual homes face heightened wildfire risk—far beyond traditionally recognized high-risk areas.

Using advanced AI models trained on over 2,000 historical wildfires, ZestyAI mapped wildfire exposure at the property level, integrating satellite and aerial imagery, topography, and structure-specific characteristics. While California leads the nation with $1.16 trillion in wildfire-exposed property, other states such as Colorado ($190.5 billion), Utah ($100.3 billion), and North Carolina ($71.2 billion) also face significant risk.

Wildfire Risk is a Nationwide Challenge

While the Western U.S. has historically seen the most severe wildfire activity, ZestyAI’s findings confirm that high-risk properties exist across the country. States like North Carolina (4.6% of homes at high risk), Kentucky (2.9%), Tennessee (2.3%), and even South Dakota (11.0%) are now seeing increased wildfire exposure.

As more homes and businesses are built in fire-prone landscapes, the Wildland-Urban Interface (WUI) continues to expand. This, combined with intensifying climate conditions, is driving higher insurance costs and growing availability concerns. Today, one in eight U.S. homeowners already lacks adequate insurance coverage, and that number is expected to rise.

AI Expands Insurance Access in High-Risk Areas

Attila Toth, Founder and CEO of ZestyAI said:

"Wildfires are threatening more properties than ever before, with billions of dollars in exposure even in areas many people don’t associate with fire risk. Yet, too many homeowners are finding themselves uninsured or underinsured just as these disasters become more frequent and severe. Insurers have traditionally relied on broad, regional models that don’t account for individual property characteristics."

"That means some homeowners are denied coverage even when their true risk is much lower than their neighbors'.’"

AI-driven risk analytics are reshaping the way insurers assess wildfire exposure. By providing granular, property-specific insights, we’re helping insurers make smarter underwriting decisions—keeping coverage available in high-risk areas while ensuring that homeowners who take mitigation steps are recognized.

Last year, our models helped insurers extend coverage to 511,000 properties that had previously struggled to secure insurance due to outdated risk models. In 2025, we expect that number to reach a million, ensuring that even in high-risk areas, responsible homeowners have access to protection when disaster strikes.

Artificial intelligence is reshaping the P&C insurance industry, offering new ways to streamline underwriting, enhance risk management, and navigate evolving regulations.

But as AI adoption accelerates, insurers must ensure they’re using these technologies effectively—balancing innovation with compliance.

Our latest guide explores the most impactful AI applications in insurance, including:

• AI-powered underwriting and predictive analytics
• How regulators are shaping the future of AI in insurance
• Best practices for integrating AI while ensuring fairness and transparency

As AI-driven tools become the new standard, insurers who adapt early will gain a competitive edge.

Download our free guide to leverage these innovations while staying aligned with evolving regulations.

ZestyAI today announced an agreement with TruStage. This partnership will leverage ZestyAI’s suite of advanced property analytics solutions for valuable insights during commercial property underwriting.

TruStage will utilize three of ZestyAI's innovative property risk analytics models: Z-HAIL™, Z-FIRE™, and Z-PROPERTY™. Additionally, TruStage will use ZestyAI's Wildfire Mitigation Pre-Fill solution in response to new wildfire mitigation regulations set forth by the California Department of Insurance (CDI) with scalable, high-accuracy wildfire mitigation data without the need for expensive on-site inspections. 

“Global insured catastrophe claims are expected to top 100 billion dollars again this year, driven increasingly by secondary perils like hail and wildfire,” said Attila Toth, Founder and CEO of ZestyAI.

“By using AI‑driven, property‑specific intelligence instead of coarse territory‑level averages, TruStage can price risk more precisely, respond to California’s new wildfire mitigation requirements, and better protect its commercial policyholders.”

Z-HAIL is an AI-powered climate risk model that predicts the frequency and severity of hail claims for every property in the US. Z-HAIL examines the interaction of climatology, geography, and the unique characteristics of every structure and roof, including accumulated damage. This information can be used in both underwriting and rating at the time of quote. Using insights into a roof’s susceptibility to severe convective storms and the potential severity of those claims, insurers can accurately segment properties by risk level. 

In addition to Z-HAIL, TruStage will use ZestyAI’s Z-FIRE product, an AI-powered, predictive wildfire risk model built on decades of real insurer loss data, and ZestyAI’s Z-PROPERTY platform, which uses computer vision and machine learning to extract insights from aerial and satellite imagery, among other unique data sources, for over 150 million residential and commercial properties.

By leveraging multiple products on the ZestyAI Climate and Property Risk platform, TruStage is empowered to make informed and transparent risk decisions and deliver best-in-class services to its valued customers.

ZestyAI, the Risk and Decision Intelligence Platform for the insurance industry, today announced that its non-weather water risk model, Z-WATER™, has been reviewed and accepted for use in underwriting and rating in Illinois, Indiana, Iowa, Louisiana, and Wisconsin. 

Insurers in these states will now be able to set property-specific rates, align coverage with home-level vulnerabilities, and target inspections and mitigation strategies—including smart water sensors—to reduce cross-subsidization and improve portfolio performance.

Non-weather water has become a major pressure point for carriers, with losses now exceeding $13 billion annually and ranking as the third-costliest peril in homeowners insurance.

Routine failures like burst pipes and hidden leaks are now producing catastrophe-scale losses that surpass hurricanes in severity. Yet the peril has been difficult to model using traditional rating tools, which rely on territory-level or age-based proxies that overlook the property-specific factors driving interior water losses.

Using verified insurer loss data, Z-WATER applies computer vision to aerial imagery and incorporates property-level data, permitting history, localized climatology, and infrastructure context to capture the property-specific drivers of interior water losses. By modeling how these variables interact, Z-WATER predicts both the frequency and severity of non-weather water claims with up to 18× greater accuracy than traditional models.

Bryan Rehor, Director of Regulatory Strategy at ZestyAI, 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.

Z-WATER helps insurers pinpoint those vulnerabilities at the property level and price them appropriately, while meeting regulators’ expectations for clarity and fairness.”

These approvals add to ZestyAI’s broader regulatory momentum. Across five perils—including wildfire, hail, wind, storm, and now non-weather water—ZestyAI has secured more than 80 approvals nationwide. Z-PROPERTY™, the company’s property and roof analytics solution, has also earned broad state-level approval, giving insurers and reinsurers trusted parcel-level insights with the same regulatory-grade transparency.

Most filing delays are self-inflicted; not by regulators, but by carriers submitting filings with missing pieces, unclear narratives, or outdated requirements. In prior-approval states, those slips don’t just slow things down; they can freeze millions in premium for months. That was the core message of ZestyAI’s recent webinar, Approval‑Ready: How Carriers and Regulators Can Accelerate Filings, featuring Carter Lawrence, Commissioner of the Tennessee Department of Commerce and Insurance, and Bryan Rehor, Director of Regulatory Strategy at ZestyAI. 

Watch the full session on demand here: Approval‑Ready: How Carriers and Regulators Can Accelerate Filings.

What regulators want from rate filings

Commissioner Lawrence opened with a simple reminder: regulators are people first, operating under clear statutory mandates but deeply focused on maintaining a healthy, competitive insurance market for the consumers they serve. 

For carriers, that means relationships and preparation matter. He urged companies to proactively meet with departments, especially before submitting novel products or complex filings that benefit from early discussion.​

Why filing delays cost insurers millions

From the carrier perspective, Bryan Rehor shared data from ZORRO Discover, ZestyAI’s agentic AI platform for competitive intelligence trained on hundreds of millions of pages of P&C filings, objection letters, and regulations. In prior‑approval states, ZORRO’s analysis shows that after the first objection, each additional objection typically adds about two months to the approval timeline, and incomplete responses can add another two to four months.​​

Those delays are often driven by preventable operational misses rather than disagreements over rate indications: missing actuarial exhibits, incomplete predictive model documentation, outdated checklists, procedural gaps, and under‑explained catastrophe assumptions. When ZestyAI’s team quantified the impact across lines, we estimated that delayed approvals translate into tens of millions of dollars per day in unrealized premium changes for the industry.​

How ZestyAI’s ZORRO Discover helps carriers become approval‑ready

The panel converged on a key idea: the industry needs to move from reactive, objection‑driven workflows to proactive, intelligence‑driven ones. For regulators, that means using technology to reduce low‑value manual review so teams can focus on complex judgment calls; for carriers, it means embedding regulatory awareness and quality checks directly into rate filing workflows.​

ZORRO Discover continuously ingests regulatory filings and related materials, so it flags gaps against current checklists, common objection themes, and emerging expectations in each state before a filing is submitted. Combined with ZestyAI’s regulator‑approved peril models and rate service organization capabilities, carriers can submit more transparent, thoroughly supported filings that earn trust and move faster through regulatory review.​​

FAQs: approval‑ready insurance filings and ZORRO Discover

What is ZORRO Discover from ZestyAI?‍

ZORRO Discover is ZestyAI’s agentic AI platform for competitive and regulatory intelligence in P&C. It analyzes 2M+ SERFF filings and related materials across all 50 states, turning millions of pages into real-time, citation-backed insights. For regulatory teams, it surfaces objection patterns and regulator expectations upfront, improving research efficiency by 20X. This helps teams run faster and more accurate pre-submission QA, draft cleaner filings, accelerate approvals, and reduce adverse selection.

How can insurance-specific AI reduce filing objections?‍

Agentic AI platforms for competitive intelligence, such as ZORRO Discover, scan millions of filings and related materials, including checklists, statutes, and historic objection letters. They help teams flag missing actuarial support, outdated checklists, weak justifications, and documentation gaps before submission. This “pre‑flight” QA reduces procedural errors that trigger avoidable objections and multi‑month delays.​​

How does ZestyAI help carriers be "approval-ready”?‍

ZestyAI helps carriers be approval-ready by strengthening both the models they file and the way those filings are prepared. Our peril models are filed through a Rate Service Organization (RSO) with standardized, regulator-tested documentation and a growing track record of approvals that carriers can reference as precedent. On the process side, ZORRO Discover provides pre-submission QA using regulatory objections and competitive insights. Together, this gives carriers more complete, regulator-aligned filings, fewer avoidable objections, and faster, more predictable approval timelines.

Why do prior‑approval states create unique challenges?‍

In prior‑approval states, rate and product changes cannot take effect until they are signed off by the Department of Insurance (DOI), so each objection round adds real financial cost as actuarially indicated changes sit idle. ZORRO Discover’s analysis shows that every additional objection can add months to the timeline, making operational quality and proactive compliance crucial levers for profitability.​

How does ZestyAI support regulators and carriers at the same time?‍

ZestyAI reduces friction on both sides of the filing process by providing regulators with better documentation and helping carriers.

For regulators:

• Standardized, RSO-filed model documentation that’s easy to review.
• Regulatory precedent from prior approvals, reducing model-review burden.
• Clear, transparent methodology aligned with statutory expectations.

For carriers:

• Faster approvals by referencing ZestyAI’s existing model approvals.
• Fewer avoidable objections through ZORRO Discover’s QA and objection-pattern insights.
• More complete, regulator-aligned filings with clearer documentation and rationale.
  

Outcome:
Regulators receive fully documented, RSO-filed models that are easier to review and validate. Carriers benefit from two advantages:

1. Clear insight into regulatory expectations to help them avoid common filing errors.
2. The ability to reference ZestyAI’s existing model approvals, which provides regulatory precedent and helps their own filings move through review more quickly.

Together, this reduces avoidable objections and creates a more efficient, predictable approval process for both sides.

To hear directly from Commissioner Carter Lawrence and ZestyAI’s regulatory experts, watch the full webinar on demand: Approval‑Ready: How Carriers and Regulators Can Accelerate Filings

‍

For insurers evaluating new data partners, transparency isn’t just about the model. It’s about the process. And at ZestyAI, that process is shaped by people who’ve actually operated inside carrier environments. Former actuaries, underwriters, product leaders, and regulatory specialists built our platform with a deep understanding of how difficult it is to integrate new technology inside a regulated ecosystem.

From day one, carriers get immediate value: full portfolio scoring, access to our web application, and the ability to validate data, explore properties, and begin applying insights right away.

Working with ZestyAI means:

• Real carrier experience behind the platform, not outsider assumptions.
• Direct access to industry experts across actuarial, underwriting, and regulatory domains.
• Instant time-to-value, with portfolio scoring and platform access available at kickoff.
• A focus on ROI, with every step designed to deliver measurable impact quickly.

Here’s what that looks like in practice — from kickoff to full production.

ZestyAI’s Onboarding Process: From Kickoff to Deployment

ZestyAI provides a structured onboarding experience aligned with your goals, whether focused on underwriting, rating, or operational efficiency. After the kickoff meeting, we work through a clear sequence designed to move fast while staying aligned with internal governance and IT workflows:

• Define objectives and use cases
• Align on data needs and file structure
• Establish integration protocols (API or batch)
• Support internal testing and model validation
• Provide regulatory guidance for rating, underwriting, and filings (state-specific documentation, actuarial support)

Our approach emphasizes speed-to-value while ensuring the process fits cleanly within your organization’s governance, compliance, and operational requirements. We don’t just integrate a model; we drive measurable outcomes such as improved segmentation, faster quoting, and operational efficiency.

ZestyAI’s models are designed to support a wide range of underwriting and rating workflows. Whether carriers use raw scores, tier bands, or mitigation indicators, the outputs align naturally with existing processes and program designs.

Integration with Guidewire, Duck Creek, Cogitate, and Other Platforms

ZestyAI is platform-agnostic and supports integration with:

• Guidewire
• Duck Creek
• Cogitate
• Custom core systems and middleware

We provide configuration support via secure APIs, batch ingestion, or prefill mapping. Our scores can be embedded into workflows across underwriting, inspection triage, mitigation eligibility, and renewals.

Data Requirements for Pilots or Backtests

To initiate a pilot or backtest, we typically request a dataset that includes:

• Property address or coordinates
• Policy effective and expiration dates
• Claims history (dates, causes, amounts)

Additional fields—such as construction type, roof material, or occupancy—can enhance model matching or segmentation. We’ll review your available data and finalize the format before ingestion.

Batch Scoring, API Integration, and Z-VIEW Access

ZestyAI models can be accessed via:

• Batch processing – ideal for backtests, portfolio scoring, and operational refreshes
• Real-time APIs – for use at quote, renewal, or mid-term policy changes
• Z-VIEW web application – a no-integration option for viewing property scores, risk drivers, and imagery

We support REST API and SFTP-based workflows, depending on your system architecture and compliance requirements. Most carriers start with batch mode and transition to real-time as production expands.

Need to evaluate before integration? ZestyAI’s portfolio scoring option enables carriers to assess entire books of business—no IT lift required.

Technical and Regulatory Support for a Custom Onboarding Experience

We offer hands-on support throughout the onboarding process, including:

• Data mapping and API testing
• Documentation walkthroughs and QA
• Score interpretation and regulatory consulting
• Workflow and dashboard design

We also provide custom analytics—such as lift charts or correlation studies—to support actuarial, underwriting, and product stakeholders across your organization.

For carriers preparing for rating or filing workflows, we also provide full regulatory support, including:

• Filing exhibits and actuarial documentation
• Dislocation and rate-impact analyses
• ASOP-aligned model memos and methodology summaries
• State-specific guidance and responses to DOI questions

Our goal is to make onboarding smooth for every stakeholder—actuarial, underwriting, product, compliance, and regulatory.

Typical Timeline to Run a Pilot or Backtest

Most pilots or backtests are completed within 4 weeks, depending on data quality and scope. After receiving your dataset, we:

• Score policies using the relevant ZestyAI models
• Analyze performance across segments (e.g., lift by decile)
• Present findings and operational recommendations
• Compare portfolio to aggregated state baselines

More advanced use cases—like rating segmentation or mitigation tracking—may require slightly more time to align with stakeholders. Regardless of scope, we aim to deliver clear, actionable insights quickly.

ZestyAI today announced that the Departments of Insurance in West Virginia, Georgia, South Dakota, Montana, Oregon, and Utah have reviewed and accepted its Severe Convective Storm (SCS) risk models, including Z-HAIL™, Z-WIND™, and Z-STORM™, for use in carrier rate and rule filings.

With these additions, ZestyAI’s SCS Suite is now ready for use in 29 states, supporting rating, underwriting, and reinsurance decisions across the most storm-exposed regions in the country.

Meeting the Growing Need for Transparent Storm Risk Assessment

As severe convective storm losses exceed $40 billion for the third consecutive year, regulators and carriers are accelerating the shift toward transparent, property-level models that clearly show what drives hail and wind losses.

ZestyAI’s SCS Suite is trained and validated on verified carrier claims data and delivers clear explanations of the factors behind each property’s risk score. By analyzing how local climatology interacts with individual property characteristics, the platform predicts the likelihood and severity of hail and wind claims with far greater precision than traditional territory or ZIP code–based methods.

Property-Level Storm Risk Models

• Z-HAIL: Quantifies hail risk using property-level drivers—roof geometry, accumulated damage, and local climatology—to pinpoint the buildings at greatest likelihood of hail damage, even within the same area.
• Z-WIND: Analyzes wind risk using AI-driven 3D analysis of roof condition, complexity, and potential failure points —together with localized wind climatology—to determine which buildings are most susceptible to wind damage.
• 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.

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

“Carriers and regulators are aligned around the need for transparent, property-specific evaluation of hail and wind vulnerability. “These filings reinforce the shift toward models that clearly explain the drivers of storm loss and support compliant, defensible decisions.”

New Capability: Mitigation-Aware Scoring

ZestyAI recently introduced Mitigation-Aware Scoring, allowing insurers to update model inputs and risk scores in real time based on verified changes to property attributes, such as:

• upgrading or replacing roof materials
• remediating visible roof or property condition issues
• correcting inaccurate data (e.g., misclassified roof type)
• modeling the impact of planned upgrades

Mitigation-Aware Scoring extends capabilities already widely used in Z-FIRE™ and ensures a consistent, carrier-controlled approach to reflecting verified improvements across perils. The functionality strengthens rating accuracy, supports fairer underwriting decisions, and aligns with evolving regulatory expectations around transparency and mitigation recognition.

‍