Microsoft Gives SQL Server R Analytics a Machine-Learning Push

By Pedro Hernandez  |  Posted 2016-03-24 Print this article Print
SQL Server

New machine-learning templates help give SQL Server 2016 customers a get a head start with advanced analytics applications based on the R language.

SQL Server 2016 features new services to enable advanced, in-database analytics. Dubbed SQL Server R Services, they integrate the popular open-source R statistical computing language used by data scientists for predictive modeling.

To familiarize enterprises with the technology's potential and help them get started on developing their own analytics applications, Microsoft has released three machine-learning templates for SQL Server R Services: Online Fraud Detection, Customer Churn Prediction and Predictive Maintenance. They are available in the Cortana Analytics Gallery and include R code, sample data and SQL stored procedure code.

Over a year ago, Microsoft made a splash when it announced it was acquiring Revolution Analytics, the Mountain View, Calif.-based leading commercial provider of R software and services. Upon the deal's completion, Microsoft revealed that it was baking R into SQL Server to enable in-database analytics services across the database software's on-premises, Azure and hybrid-cloud implementations.

Today, customers can test-drive the tech in scenarios that affect many enterprises.

"These templates are sample advanced analytics solutions that demonstrate best practices and provide building blocks to help users implement a solution quickly," said Xinwei Xue, senior data scientist manager, in a March 23 announcement. "Each template is designed to solve a specific problem, and includes sample data, R code (which uses the highly scalable Microsoft R Server ScaleR APIs) and SQL stored procedure code that extends from data preparation and feature engineering to model training and scoring."

As its name indicates, the Online Fraud Detection template helps spot transactions made with stolen payment information or compromised accounts. The data-science template teaches developers how to use data from online purchases to identify fraud using R and SQL for data processing and the R integrated development environment (IDE) for training the system and fine-tuning its scoring parameters.

The Customer Churn Prediction template is aimed at helping businesses manage and prevent the loss of customers. The code relies on customer demographics and transaction records to help determine if customers are likely to churn or stay put.

In a nod to the rapid adoption of Internet of things (IoT) technologies, Microsoft also released a Predictive Maintenance template. Using simulated sensor measurements for aircraft engines and current operating conditions, it creates three predictive model types. The template's regression models predict an engine's Remaining Useful Life or Time to Failure, while classification and multiclass classification models predict whether a component is likely to fail and when it will fail, respectively.

Beyond SQL Server, Microsoft has been working to extend R's popularity beyond the data-crunching set.

Earlier this year, the Redmond, Wash., giant released Microsoft R Server, replacing Revolution R Enterprise from Revolution Analytics, and making it freely available to students participating in DreamSpark, the company's technology in education program. A Developer Edition of Microsoft R Server, offering all the features of the paid commercial version, is available as a free download for coders wishing to explore the world of analytics applications.


Submit a Comment

Loading Comments...
Manage your Newsletters: Login   Register My Newsletters

Rocket Fuel