NCR released TeraMiner Stats, software to improve data mining processes for Teradata Warehouse customers. TeraMiner was field tested by data warehouse users and business analysts in NCR's Data Mining Lab, a low-risk consulting environment with locations in Rancho Bernardo, Calif., and Chertsey, United Kingdom. TeraMiner Stats was designed to handle the large and growing data volumes now common to most companies. Rather than using a data sample to perform data mining analysis, TeraMiner Stats can perform statistical analysis and transformations on any or all data in a warehouse. TeraMiner Stats includes scalable preprocessing components that address critical areas of data mining, including data description, derivation, reduction, reorganization, and sampling/partitioning. Customers can use all their detail-level data to perform complex data mining analyses, such as customer segmentation, propensity to buy, sales forecasting, attrition, and retention. The result is that Teradata Warehouse customers can increase their return on investment by developing more accurate predictive models in less time. "TeraMiner Stats streamlines data preparation and descriptive analysis, which typically consumes between 60 and 80 percent of a company's data mining efforts and resources before they even analyze their data," says Vickie Farrell, assistant vice president of NCR's Teradata marketing. TeraMiner leverages Teradata's ability to handle numerous multiple concurrent users and provides a single repository of analytic datasets, streamlining the data mining process by minimizing the number of steps required to analyze and manage the data. Communications, financial, transportation, insurance, and retail companies have taken advantage of NCR's Data Mining Lab facilities. The lab helps customers learn to use data mining in a secure environment. For example, Telefonica de Argentina (TdeA), one of Argentina's two telecommunications companies, wanted to explore how data mining analysis could help it face a competitive, deregulated marketplace and maintain its leadership position in southern Argentina. Data Mining Lab and TeraMiner Stats helped TdeA analyze its data with regard to customer retention, loyalty/rewards, product affinity, and product/price packaging. Now shipping, TeraMiner Stats runs on the Windows NT OS. In 2000, NCR plans to release other TeraMiner products that provide statistical and machine-learning algorithms, model deployment, monitoring, and life-cycle maintenance.