Explanation:
Azure Kubernetes Service (AKS).
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn documentation on Azure Machine Learning, the Azure Kubernetes Service is commonly used to host and deploy machine learning models, including Automated ML models, into production environments. Once a model is trained using Azure Machine Learning (Azure ML), it must be deployed as a web service endpoint so it can receive data and return predictions.
Azure ML offers two primary options for hosting and deploying models:
* Azure Kubernetes Service (AKS) - for high-scale, production-grade deployments that require fast response times, high availability, and scalability.
* Azure Container Instances (ACI) - for testing or low-scale workloads where cost and simplicity are more important than performance.
AKS provides a managed Kubernetes cluster that allows for automated container orchestration, load balancing, scaling, and monitoring of deployed machine learning models. When you use Automated ML in Azure ML Studio, the generated model can be containerized and deployed directly to AKS, making it accessible as a REST API endpoint. This enables applications, systems, or users to send data and receive predictions in real time.
The other options serve different purposes:
* Azure Data Factory is used for data integration and pipeline orchestration, not model hosting.
* Azure Automation focuses on automating administrative tasks and runbooks, not ML deployment.
* Azure Logic Apps is used to automate workflows and integrate services, not to serve ML models.
Therefore, the correct service to host automated machine learning (AutoML) models in production is Azure Kubernetes Service (AKS), as it provides a reliable, scalable, and secure environment for real-time inference and enterprise AI workloads.