Dataset shift with outlier scores
-
Updated
Feb 19, 2023 - R
8000
Dataset shift with outlier scores
A leakage-safe, walk-forward time-series forecasting stack.
An automotive after-sales churn early-warning framework with purged validation, prospective scoring, and model reliability monitoring.
R pipeline that scores a prepared client cohort to determine churn risk, quality-checks the scoring output, and writes a client-ready deck. A failing check escalates instead of shipping.
Add a description, image, and links to the model-monitoring topic page so that developers can more easily learn about it.
To associate your repository with the model-monitoring topic, visit your repo's landing page and select "manage topics."