For Data Scientists & ML Engineers · Managed Health Care

Managed Health Care Data for Data Scientists

Managed health care data for data scientists starts with Data.Medicaid.gov's CMS Medicaid Data Portal: 549 public Medicaid datasets - T-MSIS analytics, drug utilization, eligibility - pipelined through a documented DKAN REST API as monthly CSV and JSON.

financial time series api for backtesting · alternative data for quantitative research · where to get training data for managed health care models

10datasets cleared the bar for this shelf
2rated top-tier for this persona
7.6mean quality, our 10-point scoring

API, files, or your warehouse. Daily, weekly, or hourly.

How fresh is the data?

Cadence decides whether a feature is trainable or stale. Two sources are effectively static: KFF's March 2026 synthesis and the 48-row vraman54 corpus.

This beat the wider catalog comfortably: 22.6% of the 1,744 datasets Datadory catalogs.8% refresh at least weekly, yet half of this top six manages a daily or monthly cycle.

Where should you go next?

Two cautions close the loop. First, quality scores in this slice range from 4 to 9 - the weakest (vraman54, quality 4) earns its place only as an evaluation stub, not a training set.

Every dataset ranked here lives in the managed-health-care slice of Datadory's 1,744-dataset catalog, where 62.8% of all entries (1,096) score 8 or higher. Start with the managed-health-care data hub for the full industry picture, or browse all data-scientists resources to see how this vertical compares with the other industries ranked for the same persona.

Straight answers

Is there a time series API I can use for backtesting enrollment models?

Join them on state and period keys to build a backtestable enrollment panel.

What alternative data supports quantitative research on managed care?

KFF's roughly 209 state indicators add policy and enrollment covariates, and its 227-item managed-care hub surfaces new candidate sources weekly for research pipelines.

Where can I get training data for Medicaid managed care models?

Pipeline T-MSIS analytics, drug utilization and eligibility tables from Data.Medicaid.gov, join the CMS and Medi-Cal capitation and enrollment CSVs from Data.gov's managed-care searches, then extend to a longitudinal panel using the New York and California files in the Medicaid Managed Care Search.

Rows before rollout

Sample rows from any shelf entry — the field dictionary and coverage notes ride along. If the shelf misses what you need, say so; sourcing requests are half our job.

Talk to us