Saturday, October 09, 2010

SAS Offers Do-It-Yourself Predictive Analytics

Integration Developer News reports that "SAS has launched a Rapid Predictive Modeler aimed at letting business users develop predictive models for scenarios across various industries. Examples include customer segmentation, up-selling, cross-selling and campaign management, customer acquisition and customer turnover, according to SAS officials.

"SAS Rapid Predictive Modeler will let business users can generate models in a few simple steps. Specifically, business users will select data and other inputs they need to do their analysis, choose the types of outcomes and/or reports they want to see, and the SAS software will automatically process the data and select the best predictive models.

"SAS Rapid Predictive Modeler models can also be deployed in-database, which allows results to be used to make faster decisions. In specific, SAS’ latest offering provides key analytics benefits to corporations and individual business end users, including:

* Lets business analysts and subject-matter experts analyze their data using familiar UIs of SAS Enterprise Guide or Microsoft Excel.
* Provides a range of basic, intermediate and advanced prebuilt models that use a broad range of classical and modern data modeling techniques.
* Automatically treats data to handle outliers, missing values, rare target events, skewed data, correlated variables, variable selection and model selection.
* Lets users develop modeling and scoring tables using the data preparation tasks to stack, transpose, join, filter and sample data."

SAS Rapid Predictive Modeler score code is fully compatible with the SAS Scoring Accelerators for Netezza, IBM DB2, and Teradata

No comments:

Web Analytics