You develop and train a machine learning model to predict fraudulent transactions for a hotel booking website. Traffic to the site varies considerably. The site experiences heavy traffic on Monday…

Question

Options

• Aattached Azure Databricks cluster
• BAzure Container Instance (ACI)
• CAzure Kubernetes Service (AKS) inference cluster
• DAzure Machine Learning Compute Instance
• Eattached virtual machine in a different region

• A
  15% (4)
• B
  4% (1)
• C
  7% (2)
• D
  74% (20)

Explanation

NOTE: The marked correct answer (D - Azure Machine Learning Compute Instance) is almost certainly incorrect for this scenario. A Compute Instance is a single-node, fully managed development VM designed for individual data scientist use - it does not autoscale. For a production real-time web service endpoint that must dynamically scale up and down based on variable traffic (heavy on Mondays, Fridays, and holidays), Azure Kubernetes Service (AKS) inference clusters (Option C) are the correct choice. AKS supports autoscaling replicas based on load and is the recommended production deployment target in Azure ML. ACI (B) is for low-traffic testing only; Databricks (A) and a remote VM (E) are not standard AML real-time inference targets. If taking this exam, select C (AKS).

No community discussion yet for this question.