Answer-first summary for fast verification
Answer: Enable Azure Application Insights for the service endpoint and view logged data in the Azure portal.
The question requires monitoring both the data submitted to the web service and the predictions generated, with minimal administrative effort for a real-time inference service. Option B (Enable Azure Application Insights) is optimal because it provides built-in integration with Azure ML endpoints, automatically capturing request/response data including inputs and predictions, and requires minimal setup (just enabling it during deployment). It offers real-time monitoring, analytics, and alerting capabilities suitable for business-critical applications. While option D (MLflow tracking) can log predictions, it requires manual instrumentation and ongoing management, increasing administrative overhead. Options A and C do not provide real-time monitoring of endpoint traffic and predictions. The community discussion shows B as the consensus (63% votes) with upvoted comments emphasizing Application Insights' ease of setup and real-time capabilities for endpoint monitoring.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You deploy a real-time inference service for a trained model that supports a business-critical application. It is essential to monitor both the data submitted to the web service and the predictions it generates.
You need to implement a monitoring solution for the deployed model with minimal administrative effort.
What should you do?
A
View the explanations for the registered model in Azure ML studio.
B
Enable Azure Application Insights for the service endpoint and view logged data in the Azure portal.
C
View the log files generated by the experiment used to train the model.
D
Create an ML Flow tracking URI that references the endpoint, and view the data logged by ML Flow.
No comments yet.