{
  "id": 13997985,
  "title": "Soteris launches AI tool to identify insurance policies that reduce profits",
  "url": "https://urgent.news/2026/09/22/soteris-launches-ai-tool-to-identify-insurance-policies-that-reduce-13997985",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T18:52:21.000Z",
  "source": {
    "name": "Contxto",
    "slug": "contxto",
    "url": "http://contxto.com/en/insurtech/soteris-launches-ai-tool-to-identify-insurance-policies-that-reduce-profits/"
  },
  "original_language": "en",
  "account": "Soteris, an American AI startup focused on the insurance industry, has launched a new tool to help insurers identify policies that reduce the profitability of their portfolios. The product, designed at the individual policy level, aims to uncover hidden losses that traditional segment-level assessments often overlook.\n\nAs the property and casualty (P&C) insurance sector experiences changing growth conditions, with US insurers posting a $31.7 billion net underwriting gain in 2026, nearly triple the $11.6 billion from the same period in 2025, Soteris is targeting the less visible aspect of the business: policies that may be hurting portfolio performance.\n\nTraditionally, risk assessment in insurance has been conducted by grouping policies into segments with similar characteristics, allowing companies to obtain reliable metrics from large policy pools. However, this approach can conceal individual policy differences, leading to some policies within a segment generating losses while the segment as a whole performs well.\n\nSoteris' founder and CEO, Sunit Shah, explains that insurers already collect sufficient data during the application process to identify individual policy issues, but lacked the tools to analyze them effectively. The startup has been working on this approach since 2020, analyzing over 100 million policy submissions representing more than $180 billion in premiums.\n\nThe new tool moves beyond predicting loss ratios to directly estimating each policy's contribution to an insurer's profit, providing financial metrics such as EBITDA and profit. By identifying unprofitable policies, insurers can take action while maintaining the rest of their healthy portfolio. Initial proofs of concept suggest the tool can increase EBITDA by 70%-125% in analyzed books.",
  "summary": "Insurers can have a profitable portfolio overall while losing money on a portion of the policies within it. That is the problem Soteris is looking to address with a new artificial intelligence tool. The US machine learning startup focused on the insurance industry announced the launch of a profit optimization product designed to identify, at […]",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}