United StatesPublic sector2025 – ongoingCenters for Medicare & Medicaid Services
FPS2 machine learning for Medicare fraud detection
CMS reported machine learning within a fraud-screening system processing over 11 million claims daily
Problem
Medicare needed to identify suspicious billing before payment and prioritize investigations after payment.
Approach
CMS introduced the original Fraud Prevention System in 2011 and later added machine learning. FPS2 supported payment controls and ranked investigative leads using provider risk information. CMS identified Peraton as its FPS2 contractor in a 2025 update.
Results
Takeaway
The daily volume described the broader screening system. CMS did not isolate machine learning's contribution or specify when it entered use.
Categories
- Size
- Large enterprise
- Industry
- Public sector
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
CMS described operational fraud screening and investigative support. It reported daily screening volume and distinguished later machine learning from the system's original launch.
CMS listed Peraton as the FPS2 contractor. The listed performance period ran from June 2024 to June 2025.
Full details are in the original sources.