Answer-first summary for fast verification
Answer: Update the model monitoring job to use the more recent training data that was used to retrain the model.
The correct answer is B. The issue most likely arises because the model monitoring job is still using the old training data as its baseline for comparison. Updating the model monitoring job to use the more recent training data that was used to retrain the model ensures that the monitoring job reflects the characteristics of the new training data. This alignment is crucial for accurately detecting any real training-serving skew and eliminating false positive alerts.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are responsible for managing a machine learning model deployed on a Vertex AI endpoint. Recently, the Vertex AI Model Monitoring job in production triggered an alert indicating a training-serving skew. In response, you retrained the model using more recent training data and redeployed it to the endpoint. However, the same skew alert persists. What should you do to address this issue?
A
Update the model monitoring job to use a lower sampling rate.
B
Update the model monitoring job to use the more recent training data that was used to retrain the model.
C
Temporarily disable the alert. Enable the alert again after a sufficient amount of new production traffic has passed through the Vertex AI endpoint.
D
Temporarily disable the alert until the model can be retrained again on newer training data. Retrain the model again after a sufficient amount of new production traffic has passed through the Vertex AI endpoint.
No comments yet.