Geospatial Imagery and Aerial Insights - Ryan Kottenstette, Cape Analytics

Twitter icon
Facebook icon
LinkedIn icon
Insight
drone footage of house s

Founded in 2014, Cape Analytics use AI and geospatial imagery to provide intelligence to insurers. To date, they have analysed 80% of the US population, in terms of physical property risk.

The resulting data is being used by over 30 companies to help price and manage insurance policies and reinsurance portfolios.

Cape ranks as one of the best-known technology companies in insurance to have emerged in the last few years.

Drones and deep learning

In 2012 there were a couple of technologies reaching tipping points of applied usefulness.
 
Firstly, satellites, drones, and aircraft were capturing more and more geospatial imagery. Secondly, there were some major breakthroughs in deep learning and artificial intelligence specifically around being able to automatically extract information from imagery.
 
“We basically took these two tailwinds and said, where can I apply access to geospatial imagery plus deep learning analysis of that imagery, where I provide a real answer and a hard ROI to a real customer need?” said Ryan. “We quickly focused exclusively on insurance and reinsurance.”

Using data to differentiate

Having analysed physical property risk since 2014, Cape are able to compare multiple years and to run loss impact studies to actually demonstrate the monetary value associated with the insights they are able to deliver.
 
Another key differentiator is that the company extracts most of their data from imagery alone, which according to Ryan provides some real advantages.

“There's a handful of folks out there that, large incumbents and others, that have a veneer of geospatially derived data, and claiming it is unique.  In practice what's happening is they're simply appending data source from tax assessor data or other structured data sources.”
 
“This misses the whole value impact because there's a ton of value when you can capture a more recent image and understand what's changed and what's new about a given property. That's where Cape Analytics have been focused.”

Customer confidence

Although Cape don’t base their core data on third-party sources, they are increasingly using them to augment the overall picture.
 
Recently they announced a partnership with third-generation geospatial risk database creator, Hazard Hub, based in San Diego.
 
Ryan says the focus is not to append the additional data, but for Cape to apply their unique data set plus machine learning and scientific expertise to improve the overall quality and accuracy of data sets they deliver to end customers.

Cape also help their clients understand how robust their information is.

“With every data point we deliver, not only do we deliver a specific score, say a roof condition rating, but we deliver a confidence score or probability of that information being correct. This means an actuary can then take all of our scores for all of our locations and get an accurate weighted average of the confidence in the data  across an entire book of business.” 

Cape have also recognised the importance of working closely with their customers. 

“We've had the privilege of customers sharing significant parts of their loss history information with us which we've then been able to back test and validate our variables and demonstrate predictive power." 

Cape are now able to list an impressive line-up of clients willing to endorse their work, including Security First, State Auto, The Hartford, Cincinnati Financial, CSAA (part of Triple-A), Nephila Capital (part of Markel), and AXA XL.
 
“When we engage with a new carrier, we're able to show them quantifiable rigorous loss history analysis, some of which we've published. It’s basically industry-wide,” said Ryan. “And we're also able to run loss impact studies directly on their particular book of business.”

Rate Filing

One of the intiatives that Ryan is most excited about is the fact that their data is being used to support insurance rate filings.

He attributes the acceptance by state regulators, because he believes of the rigor they apply in analysing and providing data. They have already been approved in multiple states for insurers to  price insurance policies with their data.

Tackling wildfires

One growing area for Cape has been the use of geospatial profiling to analyse the risks and challenges posed by wildfires, something Ryan is all too familiar with given the company’s location.
 
“Living out here in California, we are absolutely ground zero for wildfire risk at the moment, unfortunately. The total damage associated with wildfire has just ballooned the last several years, I think everybody in our industry understands that.
 
One outcome of studying wildfire risk, according to Ryan, is that it’s demonstrated that prior forms of analysis aren’t effective.
 
“There's very clear wildfire standards published by CAL FIRE that really speak about this notion of defensible space. So we look to seewhat people have done to remove fuel loads from their property, and create a defensible space radius to protect the structure?
 
“What we've done is come up with an algorithmic way to make that information available to our customers for physical structures in their portfolio or in cedent books they might be considering and do that instantaneously at scale.”

Eyes on Europe

Having built a significant and growing business focused on continental US-based risk, Cape Analytics is looking at London and Europe, with an InsTech London breakfast event planned for the end of January.

Cape already work with customers that are Lloyd’s syndicates, plus some significant Bermuda-based reinsurers.

Eventually, he continues, Cape will be moving beyond continental US-based risks, but even before that, they’re looking at other writers, both global reinsurers as well as other Lloyd's syndicate partners, that write non-admitted direct or reinsurance as well.

This, says Ryan, represents the initial push into the London market in earnest, something he and team are very excited about.
 

You can hear Ryan in conversation with Matthew Grant on Episode 58 of the InsTech London podcast. You can also download the podcast from Spotify, iTunes and Podbean.