SPSS SHIPS NEW SmartScore CRM SOFTWARE

Your grandmother doesn't want the latest video game, and your twelve-yearold doesn't need denture cream. Sounds silly, but this kind of promotional mismatch is a common occurrence on the Web because e-retailers don't know their customers. To help companies improve customer relationships, SPSS Inc announced SmartScore, new software that applies data mining technology to help companies customize interactions at all customer touchpoints in real time. The software is currently shipping worldwide.

SmartScore is a software development kit (SDK) used to develop applications that employ the results of data mining: profiles, affinity models, propensity models, and more. These models, derived from historical and sampled data, score new cases or customers in real time based on available information. As a result, both people and systems use these scores as the basis for decisions including which products and services to present.

"Companies are challenged today, more than ever, to know and interact with their customers effectively," said David Cody, SPSS senior marketing manager. "Whether the point of contact is in the store, on the phone, over the Internet -- or more importantly, through some combination of channels -- companies need to understand who their customers are and what they want. And, they need to know this in real time, not after the fact," Cody added. "This knowledge is the key to acquiring more loyal, satisfied customers. Data mining provides the means to understanding customers. SmartScore allows companies to take that understanding to each point of interaction and use it in real time to personalize interactions and improve relationships."

Scoring begins with a model developed in another software application. For example, data miners could use SPSS AnswerTree to determine which factors predict who is most likely to purchase a given product or service. They could then export the resultant propensity model in PMML format (predictive model markup language) and deploy it throughout the organization for use in SmartScore. By gathering the relevant criteria (established by the model), various decision makers can apply and benefit from the data mining model. Decision makers, in this case, might include a Website processing online purchases, sales clerks worldwide handling in-store purchases or telesales representatives processing catalog orders.

Because PMML, a public domain extension of the XML programming language, is not a proprietary file format, SmartScore can accept models from any software package that uses it. Currently, seven models in AnswerTree and three models in SPSS 10.0 are available for deployment in SmartScore. In future releases of its data mining products, SPSS plans to make more models available for deployment in SmartScore.

"The top concern of companies doing data mining is how to get a return on their investment," said Jack Noonan, SPSS president and CEO. "An effective way to realize that return is to deploy data mining results, which is why deployment is a key strategic initiative at SPSS. We've focused a great deal of energy into making it viable, and SmartScore is the first product of that effort. What's significant for SPSS is we are the only data mining company that offers deployment."

Additional examples of how SmartScore can be used include:

• Online promotional offerings -- SmartScore can be used to deliver real-time promotional offers geared toward the distinct characteristics of Website visitors.
• Fraud detection -- To help protect against fraud, companies can use SmartScore to compare potential new customers or existing customers against profiles of prior cases of abuse.
• Risk prevention -- SmartScore can be used to instantly identify risk, such as credit, insurance or health risk, based on actual, historical customer or patient data.

Because SmartScore is an SDK, enterprises can build flexible, custom applications to fit their specific needs. Applications built with the SDK can be set up to operate in interactive mode (real-time results) or production mode. In interactive mode -- such as on a Website, in a call center or at a loan officer's desk -- cases are scored individually and the result is used immediately. In production mode cases are scored in batches and a score for each record is written back to a database for later reference. Applications can also be built to run in client/server or desktop environments. Enterprises can build their own applications or enlist help through the SPSS eMine program www.spss.com/emine.

SmartScore is a collection of java class files that offer an API (Application Programming Interface) to parse scoring models, accept a case record and provide a score result. SmartScore APIs support the following development languages: JAVA, VisualBasic (OCX), Cplus plus and C.

System Requirements

• Windows 9x, NT
• 10MB hard disk space
• 64MB RAM
• Sun Java Virtual Machine v1.2.X

Pricing and Availability

SmartScore is currently available worldwide and requires a development license and a deployment license. The development license is free and provides tools for building and testing applications as well as full SPSS technical support. Application use requires a deployment license, which costs $50,000 for use on one server or for up to 500 desktop users.

About SPSS Inc.

SPSS Inc provides solutions that discover what customers want and predict what they will do. The company delivers solutions at the intersection of customer relationship management and business intelligence that enable its customers to interact with their customers more profitably. SPSS' solutions integrate and analyze marketing, customer and operational data in key vertical markets worldwide including: telecommunications, health care, banking, finance, insurance, manufacturing, retail, consumer packaged goods, market research and the public sector.

Headquartered in Chicago, SPSS has more than 40 offices, over 900 employees and 1999 revenues of $141.9 million. The company also has won the following awards: No. 70 on Forbes 1999 list of the "200 best small companies" and as the 22nd most profitable company on the Nasdaq exchange by Equities magazine; 1999 World Class Solution award in business intelligence and named "best decision support system for business intelligence" in the 1999 RealWare award competition; No. 14 in DM Review's 1999 Data Warehouse Top 100; placed No. 23 on the 1999 Soft-letter 100, a ranking of the top 100 personal computer software companies in the United States; and No. 97 in the 1999 Software 500, a ranking of the world's largest software vendors by Software Magazine. For more information, visit www.spss.com.

Contact SPS Todd Vura, 800-525-4980 pr@spss.com.