Cloud-based machine learning platforms, like Microsoft’s Azure Machine Learning (Azure ML), provide a simplified path to create and deploy analytic solutions. Azure ML is a fully managed and secure machine learning platform that resides within the Microsoft Cortana Analytics Suite.
Azure ML workflows (known as "experiments") are constructed using a combination of drag-and-drop modules, SQL, R, and Python scripts. The wide range of built modules support the typical steps in a machine learning workflow, from data ingestion and data munging to model construction and cross validation.
Once your Azure ML experiment is ready, there are several options to deploy it. Azure ML experiments can access large-scale data stored in Azure Blob storage, Azure SQL and Hive, to name a few options. Similarly, your experiment can write results back to multiple scalable Azure storage options.
Deploying experiments as Web services is another option. Built-in tools help you deploy machine learning solutions as Web services. The Web services interface gives end users access to any Azure ML solution from Excel. Alternatively, most any BI tool with a Web services interface, including Microsoft’s Power BI or Business Objects, can access analytics through this interface.
To help you get started creating and evaluating your own machine learning models, O’Reilly has commissioned an updated and expanded report "Data Science in the Cloud with Microsoft Azure Machine Learning and R: 2015 Update." We use an in-depth data science example — predicting bicycle rental demand — to show you how to build and deploy solutions with Azure Machine Learning in the cloud. Using a free-tier Azure ML account, example R scripts, and data provided in the report, this edition gives you a hands-on experience. You’ll learn how to complete several tasks using Azure ML and R, including how to build and evaluate machine learning workflows, produce R graphics, and publish your models as Web services.
This post is a collaboration between O'Reilly and Microsoft. See our statement of editorial independence.