Answer-first summary for fast verification
Answer: Use Vertex AI Model Monitoring. Enable prediction drift monitoring on the endpoint, and specify a notification email.
The correct answer is A. Vertex AI Model Monitoring is specifically designed for monitoring ML models in production. It provides out-of-the-box functionality for detecting prediction drift, which is when the distribution of feature values changes over time. This service can automatically trigger alerts based on predefined thresholds and send an email notification, making it the most efficient and straightforward solution. In contrast, options B, C, and D involve more complex setups and manual operations and do not offer the specialized capabilities provided by Vertex AI Model Monitoring.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You have developed a regression model using tabular data and have set up a system using Vertex AI Pipelines, Vertex AI Training, Vertex AI Experiments, and Vertex AI Endpoints to train and deploy updated versions of the model. The model is currently deployed in a Vertex AI endpoint, and your users are making predictions by calling this endpoint. To ensure the model remains accurate, you need to monitor the feature data distribution and receive an email alert if it changes significantly, prompting you to retrigger the training pipeline and deploy an updated model. What should you do?
A
Use Vertex AI Model Monitoring. Enable prediction drift monitoring on the endpoint, and specify a notification email.
B
In Cloud Logging, create a logs-based alert using the logs in the Vertex AI endpoint. Configure Cloud Logging to send an email when the alert is triggered.
C
In Cloud Monitoring, create a logs-based metric and a threshold alert for the metric. Configure Cloud Monitoring to send an email when the alert is triggered.
D
Export the container logs of the endpoint to BigQuery. Create a Cloud Function to run a SQL query over the exported logs and send an email. Use Cloud Scheduler to trigger the Cloud Function.