Practice — Case Study: Churn Model, End-to-End MLOps (5 questions)

The churn model's prediction-distribution panel shows mean score drifting from 0.041 to 0.058 over two weeks. No deploys occurred in that window. Per-feature PSI shows one feature, days_since_last_login, at 0.42 — far above every other feature.

1. Walk through the specific checks you'd run, in order, to determine whether this is genuine population drift or a pipeline bug.
2. Your checks reveal that a new mobile app version stopped reporting last_login events for a specific device OS, defaulting the feature to 0 for those users. Which case is this, and what should happen next?
3. Explain concretely why retraining immediately, before completing this diagnosis, would have been the wrong move.