Data mining, data warehousing, decision support and knowledge discovery make up the universe of D S * (dsstar), the only executive business newsletter supporting strategic employment of these technologies.

The On-Line Executive Journal for Data-Intensive Decision Support
*** August 11, 1998: Vol. 2, No. 32 ***
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Article retrieval instructions are at the end of this file.
For subscription information, email dssub@tgc.com
-------------------- * --------------------

IN THIS ISSUE:

BRINGING STAT ANALYSIS AND DATA MINING TOGETHER
BY ED COLET
REPORT ON THE DCI DW WORLD CONFERENCE
BY AARON ZORNES
JOHN THOMPSON COMMENTS ON MARKETERS BUILDING MODELS

ANALYSIS & COMMENTARY

BUILDING BRIDGES BETWEEN FORMAL STATISTICAL ANALYSIS AND DATA MINING TECHNOLOGY
by Ed Colet

This week, executive editor at large Inderpal Bhandari presents a guest column by Ed Colet, a doctoral candidate presently working in the Networked Data Systems department at the IBM T.J. Watson Research Center. Ed was a member of the group that developed Advanced Scout, the data mining application for NBA teams, has taught graduate level courses on Statistical Methods, and has published papers dealing with data mining and statistics issues.

Colet writes: "Data mining and the broader area of knowledge discovery from databases (KDD) has been recognized as being a multi-disciplinary field. One of the obvious disciplines that can be associated with data mining is formal statistical analyses. Last year, the premier data mining technical conference, KDD-97, was intentionally co-located with the American Statistical Association's (ASA) primary conference in order to encourage interaction. The data mining sessions at ASA for both the tutorial and technical papers were extremely well attended and well received. Roughly one year later, it's apparent that there could still be a greater amount of collaboration between practitioners."

REPORT ON THE DCI DATA WAREHOUSE WORLD CONFERENCE, NEW YORK, JULY 28-30
by Aaron Zornes, META Group

Aaron Zornes is Executive Vice President and Service Director, Application Delivery Strategies, META Group. META Group helps companies make better information technology (IT) decisions by providing research and unlimited analyst consultation relevant to specific business needs. META Group differentiates itself from other information providers through its commitment to highly personal service (enabling "analysis in context"), bottom-line answers, and objectivity.

Zornes notes: "The audience reflected the diverse nature of applications targeted for data warehouse-style solutions. 35% percent of attendees were executive or business management and 45%+ IT professionals (consistent with DW Worlds held 2H97-1Q98); 62% are in corporate IT groups; 38% in lines-of-business IT group. 200+ attendees completed the on-line survey conducted by Market Perspectives Inc. on behalf of META Group and First Albany Corp."

WILL I AS A MARKETER EVER BUILD A MODEL?
by John K. Thompson

John K. Thompson is the Vice President of Marketing for Magnify, Inc. Thompson has over 15 years experience spanning all major technology management functions for software organizations. In his current role, as Vice President of Marketing, Thompson formulates and executes the strategic direction for Magnify, Inc. and the PATTERN product line. His technology expertise includes knowledge discovery, decision support, data warehousing, and database systems. Prior to joining Magnify, Inc., he held a number of senior technology and marketing positions at PLATINUM technology, IBM, and Metaphor Computer Systems. Thompson has consulted in Latin America, Europe, and Asia regarding the issues around building world class data warehouses and decision support systems. Thompson holds a Bachelor of Science degree from Ferris State University and a MBA in Marketing from DePaul University.

Thompson writes: "In talking, thinking, and writing about data mining I started to wonder, "Will I ever build a model of my own?" I don't mean sit down and use a data mining system to build a model for the fun of it. I've done that before. While I was at IBM, the development lab in Rochester released version 1 of what was then called the Neural Network Utility (NNU). There were about 10 of us selected to spend a week learning and playing with the software, and giving our feedback on how useful we thought the tool was. In the end, it was a fun week. We all completed our canned exercises, a few of us actually built models that read data, adjusted weights, and produced results. But, beyond being a fun exercise for people who were fairly technical, nothing of business value came of our efforts, which admittedly weren't much, nor did anything of general market value come of NNU."

ACTION ITEMS

Sagent and Unisys Deliver Data Mart Solution to Unisys Windows NT Users
Sagent Technology, Inc., provider of a leading turnkey solution for bringing data marts to the Web, has announced that Unisys Corporation is marketing Sagent's data mart solution with Unisys ClearPath Enterprise Servers and Aquanta Servers. This combined offering will help Unisys Windows NT users deploy high performance data mart applications quickly and cost-effectively.

Thinking Machines and Paragren Technologies Establish Strategic Partnership to Integrate Data Mining with Relationship Marketing
Paragren Technologies, Inc. of Reston, VA and Thinking Machines Corporation (TMC) of Burlington, MA have announced a partnership to provide "out-of-the-box" functionality for enterprise relationship marketing. The two firms will integrate and jointly market Thinking Machines' Darwin, scalable enterprise data mining software, and Paragren's One-By-One marketing suite, a set of analytical marketing applications for optimized relationship marketing. This new offering provides a seamless, automated solution that allows marketing professionals to execute targeted customer acquisition, expansion and retention strategies more effectively and efficiently. With the integration of the two systems, marketers can select and mine data using high-speed parallel data extraction routines.

TeleCheck Services Partners with Deep View Systems to Improve Check Decision-Making Accuracy with Sophisticated Neural Network Technology
TeleCheck Services, Inc. has partnered with Deep View Systems, LLC, to create the industry's first on-line neural network-based system to process all check authorizations. Neural networks, complex mathematical formulas that can "learn" from data, enhance decision-making accuracy in accepting checks at the point-of-sale and improve retailers' customer service. Currently, 180 customized networks are on-line. TeleCheck, a leading check acceptance company, is a subsidiary of First Data Corporation (FDC).

QUOTE OF THE WEEK

"Clearly, one should always explore the entire data-space of possibilities if one is able to because this presents the best possibility for discovering new knowledge."

• Ed Colet

CONFERENCES & SEMINARS 08.11.98

D S * INFORMATION

• Subscriptions & Removal information
• D S * STAFF
• INDEX OF D S * BACK ISSUES

All comments regarding editorial content should be sent to: dseditor@tgc.com