Delos uses satellite imagery and AI to help homeowners in wildfire areas get insurance

If your home is in a wildfire area, insurance companies tend to not want to go anywhere near it.

But "wildfire areas" tend to be pretty broad. What if companies could evaluate the risk on a more granular level - tapping things like satellite imagery and machine learning combined with wind, weather and topology data, to better define the riskiest zones? Could more home owners be offered policies, and at more affordable rates?

That's the idea behind Delos, a company presenting at the TechCrunch Disrupt SF Startup Battlefield today.

Delos itself doesn't act as the insurer; instead, it acts as a Managing General Agent (or MGA) for a bunch of major carriers. They analyze regions that have been broadly swept into the "wildfire area" label, with their proprietary models looking for houses that they believe have been mis-categorized. Delos reaches out to these customers, receiving a commission/profit share on any policies they sign.

The company is focusing on California first, noting that the one state accounts for half of the country's wildfires. According to CalFire, there have been over 5,000 fires in California in 2019 alone. After wildfires, Delos plans to expand to modeling hurricane risk.

Delos also regularly sends policy holders a list of things they can do to harden and protect their homes against wildfires, such as cutting back trees that overhang your home, or switching to ignition-resistant building materials. If their latest satellite imagery shows dry vegetation creeping up the hillside behind your house, they can give you a heads up of the increasing risk.

Co-founders Kevin Stein and Shanna McIntyre both have rich backgrounds in aerospace. Kevin got a Masters in Aerospace Engineering from Stanford before working as a Mechanical Systems Engineer at Space Systems/Loral, while Shanna studied physics at Berkeley before spending 11 years as an engineer at Lockheed Martin.

Stein says that he believes about 18 million homes in the U.S. are mis-categorized.