The claims model needs one governed production path, but its two rehearsals do not agree.
A fast cutover protects the warehouse exit date, while explainable scoring protects clinical confidence.
Who you’d be doing this for
“The analysts asked why yesterday’s high-risk list changed, and I don’t have one answer yet.”
Saki Ito · Claims Data Engineer
Maintains the claims feeds and supports analysts who depend on the daily risk scores.
What is at stake
Two rehearsal runs produced different claims-risk lists before a ten-day cutover window. You must weigh a faster governed path against the evidence needed to trust daily scoring.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- warehouse exit date vs. score explainability
- cutover speed vs. reconciliation evidence
- daily throughput vs. governed lineage
- clinical confidence vs. parallel-run cost
Why Databricks
Apache Spark, Delta Lake, MLflow, and Unity Catalog must operate as one production pattern for a regulated customer workload.
Written with these in mind
Not your kind of problem? 107 more at Databricks, or browse every organization.
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.