CMS launches fraud competition targeting DME claims 

WASHINGTON – The Centers for Medicare and Medicaid Services (CMS) has announced a “Crushing Fraud Chili Cook-Off Competition,” a market-based research challenge aimed at harnessing artificial intelligence, specifically machine learning models, to detect anomalies and trends in Medicare claims data that can be translated into novel indicators of fraud. 

The challenge also seeks innovative, scalable technologies that reduce labor-intensive processes while keeping humans meaningfully in the loop to ensure effective oversight and interoperability, CMS says. 

The challenge will happen in two phases: 

• Phase 1: CMS will invite research proposals from all interested parties. After reviewing submissions, 10 teams will be selected to advance to Phase 2.  
• Phase 2: Finalists will receive access to Medicare Fee-for-Service (FFS) Hospice, Part B, and Durable Medical Equipment (DME) claims data via CMS’s Limited Data Sets. Participants will apply their proposed AI/ML techniques to the data and submit a summary of their findings, as well as proposed scalable analytic and policy solutions. CMS will select and publicly announce the challenge winner. 

Timeline: 

Phase 1 

• Aug. 19, 2025 – Proposal submissions open, 12:00 AM ET  
• Sept. 19, 2025 – Proposal deadline, 11:59 PM ET 
• Oct. 20, 2025 – Phase 2 participants announced (Time: TBD) 

Phase 2 

• Oct. 30, 2025 – Data access granted to Phase 2 participants 
• Oct. 31, 2025 – Phase 2 submissions open, 12:00 AM ET   
• Dec. 1, 2025 – Final submissions due, 11:59 PM ET   
• Dec. 15, 2025 – Challenge winner announced (Time: TBD) 

FMI, see the Chili Cook-Off Challenge.gov posting.