The Challenge
Medicare pays over $1 trillion annually. Roughly $70 billion of that, about 7 cents on every dollar, is estimated to be improper payments. The GAO has repeatedly criticized CMS for lacking quantifiable fraud detection metrics. The existing model is reactive: pay first, chase later, often years after the money is gone.
The ACT-IAC 2026 AI Hackathon posed a direct question: Can AI shift CMS from reactive to proactive program integrity?
We had 13 days.
The Constraint
The team had no protected health information, data use agreements, or claims-level data. Everything had to work on publicly available CMS datasets, the same data anyone can download from data.cms.gov.
The public data contains annual totals, not individual claims. You can see that a provider billed $2.3M last year. You cannot tell whether they billed the same patient twice on the same day. Most academic fraud detection work assumes claims-level access. Our team had to work without it.
What the evidence tells us
We separate what we built from what we tested and what remains unproven. Each step toward operational use needs more evidence before the Government can accept it.
Rung 1 · Bounded challenge
A working public-data prototype under a 13-day constraint
Four people built the system without protected health information, data use agreements, or claims-level records. That demonstrates delivery speed and feasibility on public annual aggregates. Readiness for operational casework remains unproven.
Rung 2 · Historical backtest
The model concentrated known validation labels near the top
42%Backtest precision@100890xBacktest lift over random0.965Validation AUC6.9yrRetrospective lead before OIG exclusionThe team trained the model on 2013 to 2019 data and validated it on 2020 to 2023 labels. At the study's 0.047% base rate, 42 of the top 100 matched the validation label. The lead-time calculation is retrospective; it does not establish realized or guaranteed savings.
Rung 3 · Public-record corroboration
High-ranked providers matched later public enforcement records
Researchers checked every non-LEIE provider in the top 250 against DOJ releases, OIG actions, court records, and state medical boards. Thirty-seven matched documented cases involving more than $500 million in alleged or resolved fraud. These matches support further testing of the rankings. They do not establish causation or independent fraud findings.
Examples of high-ranked providers matched to public enforcement records Rank Public-record match #2 DOJ settlement of $1.2 million #7 55,000 false claims involving deceased patients #8 $14.3 million wound-care fraud case #22 $250 million opioid conspiracy #52 $6.5 million false-claims case independently investigated by ProPublica Rung 4 · Production acceptance
The Government would define and verify the operational threshold
Before production, test current authorized data, sample and label quality, ranking thresholds, subgroup performance, drift, and traceability. Also test security, privacy, Section 508 accessibility, investigator workflow, and how to handle false positives and false negatives. Government acceptance needs agreed evidence and human review. A hackathon award and one model metric cannot answer all these questions.
What We Built
A single Go binary that ingests 22 CMS datasets, scores 1.47 million providers, and serves an interactive investigation dashboard.
Indicium runs as a single Go binary on one server. It ingests 22 CMS datasets (548 million rows), scores 1.47 million Medicare providers across 10 years of history, and serves an interactive investigation dashboard.
You can look behind every score
Investigators can inspect the factors, SQL, weights, peer groups, and history behind a score. Authorized users can adjust weights to explore priorities. A score does not become an automatic finding.
Agree on what good looks like before production work
Before production work, we would agree with the Government on ranking quality, traceability, response time, accessibility, security, and usefulness to investigators. Acceptance would depend on evidence that the system meets those standards.
Model mechanicsHow public data, 27 features, and three scoring methods produced reviewable risk signals
The Data Pipeline
The system ingests data from CMS, OIG, DEA, Census, and other public sources directly into an embedded DuckDB database using CSV-to-columnar ingestion with SHA-256 deduplication. It requires no external database server or ETL orchestration platform.
| Metric | Value |
|---|---|
| Rows ingested | 548M+ |
| Providers scored | 1.47M |
| Coverage | 2013 to 2023 |
| Peer groups | 1,046 (specialty x region x year) |
| Graph nodes | 5.8M |
| Graph edges | 82.6M |
27 Features, 8 Categories
Indicium scores every provider on 27 features in eight categories:
- Billing Volume: billing far more than specialty peers, sudden spikes, solo practitioners billing like groups.
- Procedure Mix: upcoding E&M visits, concentrating in expensive codes, deviating from specialty norms.
- Drug Prescribing: opioid prescribing intensity, high-risk medications for elderly, rare drug combinations.
- Payment Network: Open Payments manufacturer relationships correlated with prescribing patterns.
- Sanctions: LEIE exclusions, Corporate Integrity Agreements, SAM exclusions.
- Geographic: billing deviation from county baselines, cross-payer risk signals.
- Graph Analysis: six custom network algorithms: prescribing isolation, opioid network contagion, manufacturer concentration, exclusion proximity, geographic deviation, co-prescribing anomalies.
- Enrichment: career stage anomalies, controlled substance supply chain deviations from DEA ARCOS data.
Three-Way Ensemble Scoring
27 features normalized to 0-100, combined with tunable weights. Deterministic, reproducible, transparent.
Isolation Forest, K-Means, Local Outlier Factor. Corroboration boost up to +30 points.
Trained on LEIE exclusion labels. Validation AUC: 0.965.
The Dashboard
The dashboard includes a national heatmap, state and county drill-downs, and detailed provider profiles. Investigators can review peer comparison radar charts, top contributing factors, 10-year billing trajectories, and network visualizations.
Investigators can adjust feature weights in real time and see scores re-rank instantly.
Every score shows exactly how it was computed, including the SQL queries, weights, and peer groups available for inspection.
A closer look at the implementation
The architecture shows how we made this prototype work and kept it manageable. Those details matter, but the Government still needs to decide whether the system meets its requirements.
Architecture detailArchitecture: one Go binary, one server, and an in-process analytical stack
DuckDB, GraphWizard, the machine-learning libraries, and the HTMX, Alpine, and ECharts interface all ran in process. The prototype therefore needed no external database or graph server at runtime.
| Component | Choice | Why |
|---|---|---|
| Language | Go | Single binary, embedded assets, goroutines for pipeline work |
| Database | DuckDB (embedded) | Columnar analytics across 548 million rows without a separate server |
| Graph engine | GraphWizard (in process) | Replaced a 100GB-RAM Memgraph dependency |
| Frontend | HTMX + Alpine + ECharts | Embedded in the binary with no production build step |
| Machine learning | Go libraries | Isolation Forest, K-Means, LOF, and GBT in process |
| Deployment shape | Single VPS | Bounded prototype footprint; production requirements remain to be defined |
Production caveat: This footprint does not establish production authorization, a security baseline, an availability design, a recovery plan, or an independent cost estimate. Those requirements depend on the Government’s data, controls, service levels, and continuity needs.
Open-source implementationGraphWizard: 82.6 million-edge analysis in about 90 seconds with a public Go library
GraphWizard was built during and after the hackathon to replace Memgraph. Its core library provides more than 40 algorithms behind standard gonum interfaces, reports 97.3% test coverage, and is available under the MIT license. The current repository has since added disk-backed graph and loading tools that use DuckDB and SQLite.
| Metric | Value |
|---|---|
| Algorithms | 40+ |
| Direct module dependencies | gonum, DuckDB, and SQLite in the current repository |
| Test coverage | 97.3% |
| License | MIT |
| Graph size handled | 82.6 million edges and 5.8 million nodes |
| Analysis time | About 90 seconds in the prototype environment |
| RAM dependency replaced | 100GB Memgraph deployment replaced with an in-process library |