Soteris, a Y Combinator-backed machine learning company focused on the property and casualty insurance industry, has officially launched after operating in stealth mode. The company has introduced a new AI-powered product aimed at helping insurance companies improve profitability.
The launch comes after more than five years of product development. Soteris has also revealed that it has raised more than $8 million in seed funding.
The funding round was led by Spider Capital, with participation from Intact Private Capital, Amplify Partners, DCVC, the Webb Investment Network and Overlook Ventures.
Soteris founder and CEO Sunit Shah said, “Every insurer knows they’re writing policies that will lose them money. They just can’t find those policies with the resources currently at their disposal. That’s the blind spot we built Soteris to close. For the first time, an insurer can look at a single policy and know exactly what it’s worth, in time to act on that information.”
Spider Capital partner Minsoo Chi said, “With his rare combination of finance, insurance, and quantitative experience, Dr. Shah is uniquely positioned to crack the toughest mathematical problems in insurance. Soteris already moved analytics from segment averages to policy-level expected loss. Extending that same resolution to predicting profit generation is the natural next step.”
Soteris uses its own machine learning technology to solve this problem. Instead of relying on a small number of insurance segment analyses created with spreadsheets, its system can create millions or even billions of different customer segments from past policy data. It compares these segments to study each insurance policy separately, giving insurers a much clearer view of their data.
The company says its technology can effectively treat every policy as its own reliable data sample. Insurers can get the system up and running within 90 days. Once live, it can analyse policies at different stages, including when a quote is created, when a policy is purchased, or later. The results can be delivered through an API in less than 250 milliseconds.
