Q: 8
Your team has a model deployed to a Vertex Al endpoint You have created a Vertex Al pipeline that
automates the model training process and is triggered by a Cloud Function. You need to prioritize
keeping the model up-to-date, but also minimize retraining costs. How should you configure
retraining'?
Options
Discussion
Option D not B. Only D triggers on real feature drift so you don't retrain for no reason.
D imo, feature drift monitoring is best to avoid unnecessary retrains. B might look cheaper but doesn't account for when the model actually needs updating. Seen similar on practice tests, pretty sure D is what they want.
C vs D? Saw similar question on practice, both seem valid but C feels right since anomaly could trigger retrain too.
C/D? Both use anomaly detection but C doesn't explicitly mention drift, so not totally sure.
Nice question, really clear scenario. B
Be respectful. No spam.
