Task 4.1: Monitor Model Inference MLA-C01 Practice Questions (Page 3)

Questions 11–15

1. 11foundation · easy

   What is a typical remediation action if a newly deployed model version shows a higher error rate than the previous version?

   • ARolling back to the previous model version.
   • BDisabling CloudWatch alarms.
   • CIncreasing the endpoint's instance count.
   • DSwitching to a different AWS region.
   Reveal Solution Discussion Select an answer first
2. 12foundation · easy

   Which AWS service is specifically designed to monitor data drift and model quality for SageMaker endpoints?

   • AAmazon SageMaker Model Monitor
   • BAmazon CloudWatch
   • CAmazon Athena
   • DAWS CloudTrail
   Reveal Solution Discussion Select an answer first
4. 13foundation · easy

   Which AWS service is used to collect and track metrics like latency and error rates for inference endpoints?

   • AAmazon SageMaker Clarify
   • BAmazon CloudWatch
   • CAmazon S3
   • DAWS Config
   Reveal Solution Discussion Select an answer first
5. 14foundation · easy

   What is the purpose of setting thresholds for inference metrics?

   • ATo log all inference requests for auditing.
   • BTo trigger alerts when metrics exceed or fall below predefined limits.
   • CTo change the model's hyperparameters during inference.
   • DTo automatically retrain the model when accuracy drops.
   Reveal Solution Discussion Select an answer first
6. 15foundation · easy

   Which AWS service can be used to send notifications when a CloudWatch alarm is triggered?

   • AAWS Lambda
   • BAmazon Kinesis
   • CAmazon Simple Queue Service (SQS)
   • DAmazon Simple Notification Service (SNS)
   Reveal Solution Discussion Select an answer first