Answer-first summary for fast verification
Answer: Azure Kubernetes Service (AKS) inference cluster
The question requires deploying a real-time web service endpoint that can automatically scale up and down to handle variable traffic patterns. Azure Kubernetes Service (AKS) inference cluster is the optimal choice because it supports real-time inference, provides autoscaling capabilities to handle fluctuating demand, and is designed for production-grade deployments. The community discussion strongly supports this with 100% consensus on option C, highlighting AKS's autoscaling and real-time support. Other options are less suitable: A (Azure Databricks cluster) is primarily for data engineering and analytics, not real-time inference; B (Azure Container Instance) lacks advanced autoscaling features; D (Azure Machine Learning Compute Instance) is for development/testing and doesn't support autoscaling or real-time endpoints; E (attached VM in different region) doesn't provide built-in autoscaling and adds latency.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are developing a machine learning model to predict fraudulent transactions for a hotel booking website. The website experiences significant fluctuations in traffic, with heavy usage on Mondays and Fridays, low traffic on other days, and high traffic during holidays. You need to deploy the model as a real-time web service endpoint on an Azure Machine Learning compute target that can automatically scale up and down to handle the variable demand.
Which compute type should you use for the deployment?
A
attached Azure Databricks cluster
B
Azure Container Instance (ACI)
C
Azure Kubernetes Service (AKS) inference cluster
D
Azure Machine Learning Compute Instance
E
attached virtual machine in a different region
No comments yet.