The Government Already Has the Data
Medicare claims, tax returns, PPP and EIDL applications — the government increasingly holds the structured transaction data that lets fraud enforcement start with a query, not a tip.
Machine-Learning
From Kaggle to MCP: Open-Source Medicare Fraud Detection
The PPP fraud pipeline worked because the SBA released unusually inspectable data. Medicare's public data is fragmented, de-identified, and missing the features detection needs. Here's what exists on GitHub, where it falls short, and what CMS would need to release to make outside healthcare-fraud analysis more practical.
The Backtest: What Excluded Medicare Providers Look Like Before They Get Caught
The previous post described a Medicare fraud backtest nobody had built. Here are the results. 289 excluded providers across 41 states, matched to pre-exclusion billing data, compared against 3.39 million peers. Thirteen of fifteen features showed statistically significant differences — and the same behavioral fingerprint shows up in never-excluded providers who have independent enforcement histories.
Building a Medicare Fraud Backtest in One Claude Code Session
A walkthrough of building a Medicare fraud backtest overnight in Claude Code — from a plain-English spec to 289 matched providers across 41 states, a fraud-similarity model with AUC 0.79, and a manual public-record check of high-scoring peers. Including the three times the pipeline failed, the data duplication bug, and the engineering decisions that shaped the final design.