deploy-models-in-production.md

title	description	documentationcenter	author	manager	editor	ms.assetid	ms.service	ms.component	ms.workload	ms.tgt_pltfrm	ms.devlang	ms.topic	ms.date	ms.author
Deploy models in production - Azure Machine Learning | Microsoft Docs	How to deploy models to production enabling them to play an active role in making business decisions.		deguhath	cgronlun	cgronlun		machine-learning	team-data-science-process	data-services	na	na	article	11/30/2017	deguhath

Deploy models in production

Production deployment enables a model to play an active role in a business. Predictions from a deployed model can be used for business decisions.

Production platforms

There are various approaches and platforms to put models into production. Here are a few options:

• Model deployment in Azure Machine Learning
• Deployment of a model in SQL-server
• Microsoft Machine Learning Server

Note

Prior to deployment, one has to insure the latency of model scoring is low enough to use in production.

Note

For deployment using Azure Machine Learning Studio, see Deploy an Azure Machine Learning web service.

A/B testing

When multiple models are in production, it can be useful to perform A/B testing to compare performance of the models.

Next steps

Walkthroughs that demonstrate all the steps in the process for specific scenarios are also provided. They are listed and linked with thumbnail descriptions in the Example walkthroughs article. They illustrate how to combine cloud, on-premises tools, and services into a workflow or pipeline to create an intelligent application.