Soteris, a YC-backed machine learning company serving the property and casualty insurance sector, has come out of stealth with a new AI-driven product designed to boost profitability for carriers and managing general agents.
The launch follows more than five years of product development and comes alongside the disclosure that Soteris has raised over $8m in seed funding.
The round was led by Spider Capital, with additional backing from Intact Private Capital, Amplify Partners, DCVC, the Webb Investment Network and Overlook Ventures.
Soteris’s original offering, which has been helping carriers and MGAs sharpen their loss ratios since 2020, has already scored more than 100 million policy submissions covering upwards of $180bn in premiums, growth the company attributes to founder-led sales rather than marketing spend. Its newly unveiled AI profit optimisation tool goes a step further, aiming squarely at insurers’ bottom lines by identifying individual policies that quietly drag down profitability, something that has traditionally been near-impossible to spot.
The problem Soteris is targeting stems from how the insurance industry has always had to measure risk. Because insurers don’t learn the true cost of a policy, its claims losses, until long after it has been sold, they have relied on grouping similar policies into segments and treating any variation inside those groups as statistical noise. A segment only becomes reliable once it contains enough policies, meaning the performance of any single policy gets lost in the average.
Soteris says this creates a substantial blind spot, one that consultancy research has linked to underwriting gains of 30 to 50% when insurers act on portfolio pruning and profitability recovery in segments that otherwise look fine on paper.
Soteris’s proprietary machine learning approach is built to close that gap. Rather than the handful of credible segment analyses typically produced through spreadsheets, its models generate millions, sometimes billions, of simultaneous segmentations from a policy history, cross-referencing them to assess each policy individually. In effect, this turns every single policy into its own credible sample size. Insurers can put the system live within 90 days, after which it delivers analysis at any stage of a policy’s life, quote, bind, or afterwards, in under 250 milliseconds via an API.
Customers using Soteris’s original loss-ratio product have reported improvements of five to 15 points within a year of implementation.
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.”
Copyright © 2026 FinTech Global
