The Centers for Medicare and Medicaid Services (CMS) on August 19 launched  what is described as a “new market-based research challenge” targeting fraud opening a month-long submissions opportunity.

The “Crushing Fraud Chili Cook-Off Competition” aims to harness explainable artificial intelligence (AI), specifically machine learning (ML) models, to detect anomalies and trends in Medicare claims data that can be translated into novel indicators of fraud. This challenge also seeks innovative, scalable technologies that reduce labor-intensive processes while keeping humans meaningfully in the loop to ensure effective oversight and interoperability.

There will be two phases to the competition. In Phase 1, CMS is inviting research proposals from all interested parties between August 19 and September 19. A neutral third-party evaluation panel, composed of subject matter experts selected by CMS, will select 10 teams to advance to Phase 2 – the competition.

In Phase 2, on October 30, 2025, the 10 finalists will be granted access to limited data sets on Medicare fee-for-service Hospice, Part B and Durable Medical Equipment data and they will use their proposed AI/ML techniques to analyze the data. They will then  submit their summary findings, other scalable analytics and policy solutions by December 1, 2025 in compliance with the requirements of the data use agreements.

The winners of the challenge will be announced on December 15, 2025. There is no monetary prize for the competition. CMS will publicly recognize the 10 finalists and the Crushing Fraud Chili Cook-Off winner for their innovative solutions on CMS social media channels.

Participants are welcome to leverage these innovations for any future contract bids that CMS announces.