The Evolving Landscape of Homeowners Insurance

The homeowners insurance market is under intense pressure due to a combination of factors:

• Population Shifts and Real Estate Development: Growing populations and new developments in high-risk regions exacerbate underwriting difficulties.
• Unpredictable Weather: Increased frequency and severity of weather-related events make risk prediction more complex.
• Market Disruptions: Factors like social inflation, macroeconomic pressures, rapid innovation demands, and heightened competition are intensifying the strain on insurers. Litigation management costs surged 19% from 2018 to 2023 for the combined P&C sector, reflecting an approximate $24 billion loss adjustment expense (LAE).

These issues are compounded by a surge in consumer insurance shopping, a rise in higher-risk policies, and an increase in long-time policyholders switching carriers. Insurers are forced to make tough choices, such as raising premiums, exiting markets, or discontinuing certain coverage lines. These pressures are preventing the industry from achieving necessary positive outcomes critical for future profitability.

The Burden on Underwriters

Amid the ongoing market uncertainty, underwriters particularly are facing significant challenges:

• Overwhelming Submission Volume: An influx of submissions strains underwriting resources.
• Inaccurate Risk Prediction: Traditional methods based on demographic data and zip codes are proving to be inadequate, necessitating more precise risk assessment tools.
• Data Quality Issues: Poor-quality or unstructured data and manual processes further complicate risk assessment.

Underwriters are questioning why the process is so burdensome and how it can be alleviated. The crux of the issue is underwriting profitability, crucial for maintaining healthy bottom-line results. Fortunately, there are modern solutions to address these goals.

Modernize Risk Assessments with Behavioral Predictions

Traditional underwriting relies heavily on demographic data and location. Enhanced risk assessment goes beyond traditional methods such as ZIP Codes and credit scores by incorporating individual behavior and decision-making patterns.

Underwriters today can access a wealth of data outside traditional risk variables to deepen the understanding of their policyholder’s risk profile. By utilizing AI-powered behavioral predictions, which incorporate information about consumer activity, interests, buying choices, etc., underwriters can more accurately predict outcomes relevant to insurance underwriting performance.

To remain competitive, insurers must invest in this digital transformation and reduce reliance on complex, manual processes. In fact, a McKinsey analysis found that the most successful carriers are those leveraging the latest technologies to optimize underwriting capabilities. Enhanced approaches for success involve adding:

• Comprehensive Risk Profiles: A detailed view of prospective and existing policyholders to start transforming underwriting workflow.
• AI and Person-Level Insights: Using AI to access powerful person-level insights about customers and their individual risk propensities, which directly impact underwriting profitability.

Leveraging Behavioral Predictions Across the Insurance Value Chain

Using behavioral intelligence represents a transformative shift in insurance underwriting. By incorporating policyholder behaviors into risk evaluation, insurers gain a deeper understanding of risk profiles and individual customer nuances, leading to a more customer-centric approach to coverage. This intelligence offers specific predictions that enhance risk assessment:

• Identifying policyholders with a high propensity to seek an attorney at first notice of loss (FNOL) or a likelihood to litigate.

• Predicting claims frequency and severity for current policyholders and prospective customers.

• Assessing the likelihood of non-payment or early cancellation.
• Determining which prospects are most likely to convert to new customers and predicting their lifetime value.

When insurers identify policyholders with a higher propensity for risk, they can proactively manage these policies more precisely using unique identifiers. Meanwhile, they can handle other policies based on different qualifiers that indicate varying levels of risk. This becomes a game-changer for insurers’ ability to predict and review for underwriting.

Empowering Underwriters

Underwriters are tasked with building profitable books with targeted risk profiles. To be successful, they need to make quick, effective, and accurate assessments of the profitability of each policyholder. However, they are often working with limited or convoluted information and are under considerable time constraints.

Utilizing person-level intelligence in underwriting allows underwriters to focus their craft and expertise on the most complex risks. By integrating person-level intelligence, insurers can:

• Identify High-Risk Insureds Early: Early identification of high-risk individuals allows underwriters to focus on the most complex cases, improving resource allocation.
• Improve Efficiency: With simply using a name and address, significant risk insights can be obtained in seconds.
• Enhance Risk Handling: Focus on complex cases while automating the handling of low-risk applications, improving overall workflow efficiency.
• Provide Personalized Service: Offer coverage tailored to individual risk profiles, moving beyond traditional factors like location and credit scores.

Future-Proofing Insurance Underwriting

For P&C insurers, integrating person-level intelligence into underwriting processes offers a more precise and complete view of the policyholder risk profile. This approach helps insurers better prepare for uncertainty, respond to market volatility, avoid adverse selection, and achieve profitable, sustainable growth. These AI-powered behavioral predictions empower insurers to:

• Predict and Manage Risks More Accurately: Identify high-risk individuals earlier and adjust policies accordingly.
• Enhance Customer Understanding: Gain insights into customer behavior, such as propensity to litigate or likelihood of early cancellation, improving risk management strategies.
• Improve Underwriting Profitability: Achieve more accurate risk assessment and better manage underwriting resources, contributing to healthier bottom-line profitability and sustainable growth.

Using Advanced AI Risk Assessment with Pinpoint Predictive

A more comprehensive and inclusive risk assessment requires a deep understanding of the individual behind the policy, as well as incorporating insights into an insurer’s decision-making processes as part of risk analysis.

Pinpoint Predictive empowers underwriters by enabling them to make smarter, more equitable assessments of risk, accurately identifying high-risk and low-risk individuals. This enhanced accuracy in underwriting workflows helps insurers better serve their customers by identifying and quantifying individual risk earlier and more accurately.

By bridging the gap between the most powerful behavioral predictions made by the world’s leading tech companies and the specialized requirements of the insurance industry, Pinpoint is delivering unmatched risk-selection capabilities at various points along the insurance value chain.

Conclusion

The homeowners insurance sector faces unprecedented challenges. Behavioral intelligence, centered on individuals, represents the next generation of technology, transforming policyholder risk assessments and offering insights into future customer risks. As the industry adapts to these new technologies, the focus will shift toward more informed, efficient, and customer-centric underwriting practices, paving the way for a more resilient and profitable insurance market. Insurers that integrate these advanced risk assessment tools and insights will ultimately be the most successful in enhancing their underwriting processes, addressing the evolving risks associated with new developments and weather events, and ultimately improving financial outcomes.

Improve your Underwriting Outcomes with Pinpoint

With predictions available earlier and more accurately than any other risk solution on the market, Pinpoint is transforming the P&C insurance industry and helping underwriters drive better outcomes with an AI-powered, real-time solution for precise risk selection. For more information about how Pinpoint can help you, visit www.pinpoint.ai or contact info@pinpoint.ai.

The post Addressing Homeowners Underwriting with Behavioral Risk Predictions first appeared on AAIS.

AI Game Changers for Underwriters

With extensive industry experience and a keen eye on the evolution of technology platforms, particularly in AI and underwriting, Schaendorf identified numerous use cases for carriers, especially in underwriting and claims. She also sees significant potential in data access and utilization. Currently, data is often presented in static reports or dynamic formats, but AI has the power to transform how data is interpreted and interacted with.

Advancing Predictive Modeling in Underwriting and Claims Processes

In addressing the future of predictive modeling, Schaendorf explained how Cogitate focuses on its application in underwriting. “We’re looking at the profile of our risks, specifically the risk attributes that come in with each different type of client,” she said. While there are similarities in some variables, many are distinct, and Cogitate’s goal is to use these data attributes to build models that predict outcomes. For instance, Cogitate aims to determine the propensity for a loss ratio based on specific risk attributes.

On the claims side, the objective is to value claims accurately, especially complex ones. “It’s easy to handle the least complex claims, such as glass and towing in auto, but when it [comes] to a case that’s going to go to litigation, how do you set the reserves on that and what does that look like over the life of that claim?” Schaendorf proposed. “I see the ability to use that data and predictive modeling to get a little more accurate and a little better at it.”

Biggest Data Challenges Carriers Face and How to Overcome Them

According to Schaendorf, the biggest challenge carriers face when it comes to data is its structure and accessibility. While some data, like written premiums, policy numbers, and loss ratios, are well-structured, other types are not. This lack of structure poses significant difficulties in obtaining better, more accurate, and more useful data. To address this, Schaendorf believes it is crucial to foster a strong partnership between data professionals and top leadership within a company. “One group has one set of skills, and the other group has the business knowledge,” she explained. Although establishing these standards is time-consuming and may not seem immediately rewarding, they ultimately facilitate faster and more accurate data access.

About Cogitate

Cogitate was formed in 2012 by Schaendorf and her co-founder, Arvind Kaushal, as a digital platform operating on a software-as-a-service model. It is designed to streamline rating, quoting, binding, and issuance across all lines of business, including both commercial and personal lines. This modern-facing platform boasts numerous third-party data integrations, enhancing its functionality. “The proudest thing I can say about Cogitate is it’s an enabler,” Schaendorf shared. Cogitate has seen rapid growth and implementation success with their clients, processing a significant volume of quotes, binders, and premiums through the platform across various lines, such as commercial transportation, personal property, flood, commercial property, and professional liability. “It’s really facilitating growth for our partners, and that’s what we’re most proud of with the company.”

Learn more at Cogitate.com.

To view the full interview with Jacqueline Schaendorf, CPCU, click on the video above.

The post AI, Predictive Modeling, and Data Trends in Underwriting first appeared on AAIS.

Creation of Hurricane Models

According to Fanoe, hurricane models are generally a merge of meteorological expertise, engineering expertise, and insurance expertise. “Most models will start with the [meteorological] portion of the model, which is projecting out potential hurricanes, determining the frequency with which they’ll occur, and the path they’ll take if they do occur,” said Fanoe. “Then, we project the path [a hurricane] will take, including where it will make landfall, what will happen once it makes landfall, and how much the wind speed will slow down.” Then, there is the wind field assessment, which determines what areas are being affected and by how much wind. “This allows you to map out all of the homes and buildings that are impacted by wind and how much wind there is,” said Fanoe. “Wind fields feed directly into the [engineering] component of the model.” The combination of the meteorological and engineering components produces an estimate of how much damage is done to every home within the wind field of the model, which leads to insurance expertise. “This component looks at what homes are written by an insurer, what the limits are on those homes, and what the deductibles are on those homes,” Fanoe explained. “What the overall limits are is how reinsurance comes into play. That is used to project the loss that a particular insurance company is going to take related to that storm.” While this is a very simplified take on how hurricane models work, it is important to understand that since they utilize meteorological, engineering, and insurance expertise, it takes multiple different experts to create them. There also can be a lot of different versions of these models. That being said, almost every model will have a long-term and short-term version of that model. “The only difference between the long and short-term versions of the model is in the frequency assessment of the hazard model,” Fanoe shared. “A long-term model will use usually 100-year or more averages of the actual landfall rates of hurricanes in the U.S. to project that frequency. A short-term model will be based on shorter-term averages.”

How Insurance Companies Use Hurricane Models

Since hurricane models are very complicated, Darby revealed that the Maine Bureau of Insurance requests information on each CAT model in the filings as well as the version number that they’re using for their CAT load. Then, they look down to the Florida Commission of Hurricanes to see if they’ve approved that model. If Florida has approved it for use in Florida, then Maine allows it for use in their rate filings. “We follow this process because I do not have the expertise to review the CAT model as it is,” Darby explained. “That being said, we do have 3,500 miles of coastline here in Maine, and even though our hurricanes are usually category one or two, we’re still concerned about having a large coastline in the future.” With this in mind, it is important that insurance companies are building in enough load in their rates so that they maintain solvency.

Education & Regulation of Hurricane Models

While some states, like Maine, do not have a coastline that is much impacted by severe hurricanes, Gupta believes it has become increasingly important for regulators to build knowledge and understanding of CAT models. “[Regulators] are key stakeholders when it comes to managing the insurance marketplace within their states,” she said. “They need to ensure that their markets are healthy and solvent with increased catastrophic and climate risk and that there is availability and affordability of insurance.” Historically, the knowledge and understanding of CAT models have been limited in the regulatory community for many reasons. “One is simply the lack of access to model documentation due to the proprietary nature of these commercial CAT models,” Gupta shared. “So, the documentation or the knowledge doesn’t exist in a public state that is readily available for regulators.” The other, she explained, is the fact that these are complex models. “There are not enough standard resources that exist within individual state DOIs and within the NAIC around these CAT models,” Gupta stated. She is currently trying to change this with her work at the NAIC. Gupta’s role focuses on bridging the educational gap and building knowledge within the regulatory community. “We have actually developed a foundational course around these CAT models that is peril agnostic,” she revealed. “The course focuses on different components of the CAT model framework, the input-output, and the application of CAT models.” The NAIC plans to expand this training program to specific perils, which will go more in-depth depending upon individual states’ needs.

If you would like to view the presentation again in its entirety, please click the video above.

Questions? Please don’t hesitate to reach out to any of the featured speakers through the contact information below.

Linda Jancik
Product Manager – Personal Lines (AAIS)
lindaj@aaisonline.com

Greg Fanoe, FCAS, MAAA
Director & Consulting Actuary (Davies)
gfanoe@merlinosinc.com

Sandra Darby
Property & Casualty Division Actuary (Maine Bureau of Insurance)
sandra.c.darby@maine.gov

Shaveta Gupta, CPCU, ARM, ARe, CCM, CCRMP
Catastrophe Risk & Modeling Advisor (NAIC)
sgupta3@naic.org

The post Webinar: Hurricane Models – Creation, Usage, and Regulation first appeared on AAIS.