NEW REFERENCE ARCHITECTURE: Build a real-time recommendation API on Azure

This post has been republished via RSS; it originally appeared at: Azure Global articles.

First published on MSDN on Dec 20, 2018
We have a new AI Reference Architecture (on the Azure Architecture Center ) from AzureCATs Nikhil Joglekar , Miguel Fierro , and Max Kaznady .  It was edited by Nanette Ray and Mike Wasson . Reviewed by AzureCATs Tao Wu , Danielle Dean , Emmanuel Awa , and Le Zhang .


This reference architecture shows how to train a recommendation model using Azure Databricks and deploy it as an API by using Azure Cosmos DB, Azure Machine Learning, and Azure Kubernetes Service (AKS).



This reference architecture is for training and deploying a real-time recommender service API that can provide the top 10 movie recommendations for a given user.

This Reference Architecture includes the following information:

  1. Architecture - Explaining the different elements of the architectural diagram.
  2. Performance considerations - What to watch out for to maintain high levels of performance.
  3. Scalability considerations - A survey of a few Azure services to scale according to your unique needs.
  4. Cost considerations - How pricing works across the services.
  5. Deploy the solution - Instructions and access to our Microsoft Recommenders repository, with more information, instructions, scripts, and notebooks.


Head over to the Azure Architecture Center to learn more about this reference architecture, Build a real-time recommendation API on Azure .

 

See Also

Additional related AI Reference Architectures:


Find all our Reference Architectures here.

 


 
AzureCAT Guidance
"Hands-on solutions, with our heads in the Cloud!" 

Leave a Reply

Your email address will not be published. Required fields are marked *

*

This site uses Akismet to reduce spam. Learn how your comment data is processed.