11 min read

Next-Gen Property Insurance Prefill Intelligence: What Is It & How Can It Give Underwriters an Edge?

Hearing about recent advances in property insurance prefill technologies but unclear about how they work and what to look for in a solution? In this post, we’ll explore the challenges found with many existing prefill solutions and how new innovations from CAPE can allow carriers to better assess risk from the very beginning of the policy lifecycle.

What Is Property Insurance Prefill?

Insurance prefill is an approach to automatically populating insurance applications with detailed property information to reduce the amount of time and manual work required to fill out coverage applications.  

For insurers, this is no small matter. As far back as the 1970s, insurance companies realized the onerous process of asking homeowners dozens of questions in order to calculate an appropriate premium to match the risk was creating a number of issues.

Asking homeowners dozens of questions wastes a lot of time for both consumers and agents. It also reduced total quote volume—leaving insurers vulnerable to nimbler competitors. The answers provided by homeowners were also sometimes incorrect, creating a potentially costly mismatch between premium and actual risk. In turn, this created greater exposure for insurers while also leading to chronic levels of underinsurance that can be financially ruinous for policyholders. 

As a result, insurance companies began experimenting with using computers to automate and streamline certain aspects of the underwriting process by leveraging data that was often already housed in databases to give homeowners a place to start. Relatively straightforward forms of automation could be used to prefill this information and lead the homeowner in verifying or correcting information and increasing speed to quote and total quote volume significantly.

But this approach had its own limits. As has always been the case, homeowners continued to lack even basic information about things like living area, the age or condition of the roof, or type of foundation. But because available data used by automation was typically drawn from public municipal and county databases, local real estate records and eventually things like building permits were added into the mix. These sources provided a high fill rate for some fields, but weren’t all that reliable for others. And because the quality of records could vary from one area to the next, insurers ended up accelerating a process that led to the same kinds of mismatches they were trying to avoid.

Through the 1980s and ‘90s, it also became clear that even when data was reliable, insurers had limited ability to understand the connectivity and knock-on effects of different exposures—let alone the technology to piece it together. As more sophisticated analysis and modeling for risk such as natural catastrophes emerged in the 2000s, vast amounts of accurate data increasingly became available to insurers—along with new ways of collecting and sharing it. 

Fast-forward to our post-pandemic, digital-first world of property insurance, and consumers have little tolerance for anything short of instant gratification when shopping for coverage. Whether they’re connecting online or through a call center, they expect a swift, painless, and transparent experience from every business they transact with—including insurers

But challenges remain. Yes, enormous troves of information on property condition, the prospective customer, replacement costs, and more have become widely available. But an inability to make sense of a sea of unstandardized, disparate, and often contradictory data sources can lead to their own costly mistakes. 

The same is true of systems designed to streamline policy quoting and renewals by not raising flags that might result in higher premiums and sending customers fleeing for competitors in a marketplace where the lowest premiums usually win. Consider that replacement cost estimations are often not reviewed or updated at renewal, and the impact of rampant inflation, and the result is increased rates of underinsurance. 

In fact, a recent CAPE study found that as many as 25% of all properties in a typical insurer’s book of business contained substantial errors in key replacement cost drivers. When these cost estimations are too low, underinsurance can reach precarious levels. Likewise, overestimated replacement costs can result in a higher-than-necessary premium. These customers will likely churn when a data-savvier insurer gets the estimate correct and quotes a more appropriate premium.

Enter solutions like CAPE Purefill. Through the development of our own next-generation prefill solution, we’ve been identifying the most challenging aspects of existing prefill offerings and solving them—removing the risk that comes with under- or over-estimation of replacement costs. 

How Does CAPE’s Prefill Solution Work?

CAPE’s prefill technology brings together an array of traditional data sources, including public records and data from home sales, and combines it with insights derived from multi-angle, high-resolution imagery and additional, novel data sources. This up-to-date property intelligence  includes sophisticated aerial and satellite imagery. 

Through a fusion of advanced machine learning (ML) and high-resolution imagery, our technology can process and make sense of large amounts of unstructured data and make highly-accurate predictions about the risk associated with a specific property available instantly and reliably to underwriters. 

By improving the accuracy and dependability of home insurance prefill, we make it possible for insurers to accurately estimate replacement costs and match premium to true exposure. 

What Are the Benefits of CAPE’s Prefill Solution?

Our solution is currently available in two versions:  

Purefill: Outlier Detection scans both prefill and user-entered information to ferret out data anomalies during the policy quote flow, so it can be corrected quickly and easily—reducing the need for post-bind changes. 

These anomalies can include errors in the key drivers of replacement cost and coverage decisions—including living area, quality grade, and the number of stories or the presence of one or more garages. Through both ortho (overhead) and oblique (45-degree) aerial imagery, for instance, CAPE’s solution can verify or refute the accuracy of data records used in other prefill solutions. 

These capabilities also help insurers identify existing policies with potentially incorrect Coverage A estimations, enabling them to make necessary corrections across portfolios. Where existing cost estimations are too low, the insurer has an opportunity to identify them and capture a higher premium while ensuring the customer has the appropriate Coverage A. When too high, the insurer can recalibrate to an appropriately competitive premium.

Purefill: Complete Prefill offers machine learning-powered data for over 25 of the most essential home RCE inputs and can replace insurers’ existing solutions or in-house operations. By ensuring a better match between premium and true exposure, our complete prefill solution generates faster, more accurate information at a higher fill rate.

The solution also includes reliability indicators that insurers can use to determine when it’s safe to depend on prefill. When fields cannot be prefilled with a high level of confidence, the solution will provide an estimated range (or “confidence interval”) for some property features, while in others, it will generate a best-estimate based on sources such as aerial imagery. 

When confidence scoring is too low, the solution will prompt the insurer to pursue other data sources, engage with the homeowner to collect more information, or order an in-person inspection.

More Than Just Smart Business

CAPE’s prefill technology may also have significant societal value. Today, 85% of US homeowners have property insurance—nearly 80% of which entails an HO-3 policy that covers any cause of damage other than those expressly excluded. Yet despite the wide availability of accurate, up-to-date property risk data, two-thirds of those policyholders could face financial ruin if a catastrophic event damages their home.

According to the Insurance Information Institute, more than 66% of all US homes are “woefully underinsured” against wildfire, for instance. On average, those homes are underinsured by 22% but can run as high as 60% or more. Overall, 6 in 10 homes are underinsured regardless of peril—including wind, hail, and theft and more. The average undervaluation tops 17%. 

Also a growing problem: Inflation. According to LendingTree, the average cost of rebuilding a home is $36,000 higher than in 2020. Just 30% of homeowners have increased coverage limits or purchased more insurance to compensate for rising building costs, according to a survey from The Harris Poll

Property insurance prefill intelligence drawn from granular, high-quality data sources and assessed by AI models can help insurers close the coverage gap and account for inflationary pressures while fostering customer trust and loyalty. 

Prefilling New Opportunities

For one thing, insurers can price their coverage competitively versus pricing themselves out of the market or writing off entire neighborhoods or zip codes due to a lack of visibility into property-specific risks. 

With better visibility into actual exposure, they can determine accurately-priced premiums that allow them to offer guaranteed replacement policies that cover all rebuilding costs. Or they could provide extended or enhanced coverage that pays 25% more than the limit on a standard HO-3 policy, for example. 

By automatically populating applications and renewals with accurate, up-to-date information, property insurance prefill intelligence enables insurers to become proactive partners in helping protect customers from perils and unwanted surprises. 

To learn more about leveraging modern property insurance prefill intelligence to better match premium to true exposure from CAPE Purefill page here.