SAS Speeds Text Analytics and Information Discovery with Taxonomy Kits

by Vangie Beal

The new SAS Industry Taxonomy Rules starter kits improve the speed to value from text analytics and unstructured data.

Business analytics leader SAS has announced new pre-built Industry Taxonomy Rules starter kits for SAS Enterprise Content Categorization. The new taxonomy add-ons, according to SAS, can cut the implementation time for text analytics from months to weeks.

SAS' text analytics framework enables organizations to maximize the value of information within large quantities of text. The company said its new Taxonomy Rules starter kits improve the time to value from the automatic classification of unstructured, textual data and from text analytics efforts as a whole.

"Taxonomy defines the classification of documents into different categories, and when you build a taxonomy, you need to create rules to accurately classify your documents," said Fiona McNeill, product marketing manager for SAS Global Text Analytics. "Building taxonomies from scratch can be daunting. But with the new SAS Industry Taxonomy Rules starter kits, organizations get a jump start, and can move more quickly from document and text chaos to value and insight from their unstructured data."

To categorize unstructured, textual data archives, organizations would typically face a time-consuming manual process of defining the initial terms, characteristics and interrelationships. SAS Industry Taxonomy Rules starter kits include SAS-defined starter rules and baseline definitions from WAND Inc. to offer plug-and-play capability.

"SAS taxonomies offer attributes and attribute values in addition to concepts and terms," said Ross Leher, CEO of WAND. "The difference in clarity is like night and day. This level of detail goes well beyond the information conveyed in a headline or the first few sentences of a document. The SAS Industry Taxonomy Rules starter kits build upon WAND taxonomy expertise and help organizations quickly derive value from categorization. Thanks to their out-of-the-box implementation, ROI is almost immediate."

With the taxonomy starter kits, SAS said implementation teams can focus on building more complex rules for the organization's document collection, classification and analysis. They can also help decision makers quickly find the information they need in text data to respond to opportunities and make better business decisions.

Organizations benefit from categorizing massive volumes of text, as it improves response times when applied to any form of electronic documents, such as research and financial archives, patient histories, customer servicing records, job applications and Web content. These unstructured, textual data archives can provide valuable insights on customer activity.

SAS said its Industry Taxonomy Rules starter kits will be available in more than 30 languages and target major industries such as banking and financial services, retail, health and life sciences, and automotive manufacturing.


  This article was originally published on Friday May 20th 2011
Mobile Site | Full Site