PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #329
You developed an ML model using Vertex AI and deployed it to a Vertex AI endpoint. You anticipate that the model will need to be retrained as new data becomes available. You have configured a Vertex A
The correct answer is D. Enable request-response logging for the Vertex AI endpoint, and set up alerts using Cloud. Enabling request-response logging allows Vertex AI Model Monitoring to track predictions and input data over time, which is essential for detecting feature attribution drift. Setting up alerts in Cloud Logging ensures timely notifications when drift is detected. The Google Cloud
Question
Options
- ASet up alerts using Cloud Logging, and use the Vertex AI console to review feature attributions.
- BSet up alerts using Cloud Logging, and use Looker Studio to create a dashboard that visualizes
- CEnable request-response logging for the Vertex AI endpoint, and set up alerts using Pub/Sub.
- DEnable request-response logging for the Vertex AI endpoint, and set up alerts using Cloud
How the community answered
(46 responses)- A4% (2)
- B15% (7)
- C7% (3)
- D74% (34)
Explanation
Enabling request-response logging allows Vertex AI Model Monitoring to track predictions and input data over time, which is essential for detecting feature attribution drift. Setting up alerts in Cloud Logging ensures timely notifications when drift is detected. The Google Cloud console provides built-in tools to review feature attribution metrics, supporting continuous evaluation.
Topics
Community Discussion
No community discussion yet for this question.