The On-Line Executive Journal for Data-Intensive Decision Support
*** November 4, 1997: Vol. 1, No. 5 ***
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Article retrieval instructions are at the end of this file.
For subscription information, email dssub@tgc.com
-------------------- * --------------------
IN THIS ISSUE:
ROGER STEIN DISCUSSES THE EXECUTIVE PERSPECTIVE ON DATA MINING
DATA PROSPECTING VIA UNSUPERVISED ADAPTIVE CLUSTERING BY BEN HITT
INFOMODELERS' TOM VAN HORN TALKS ABOUT DATA MINING COMPLEX PROFILES
ANALYSIS & COMMENTARY
DATA MINING AND KNOWLEDGE DISCOVERY FROM THE EXECUTIVE PERSPECTIVE:
AN INTERVIEW WITH ROGER STEIN
by Alan Beck, editor in chief
Roger Stein is vice president, senior credit officer, Quantitative Analytics, Moody's Investors Service. He is co-author with Vasant Dhar (former principal, Morgan Stanley and associate professor, New York University) of the book "Seven Methods for Transforming Corporate Data into Business Intelligence," (Upper Saddle River, NJ, Prentice-Hall, 1997) that shows how to apply intelligent and adaptive systems to business problems. (See D S * article 100003, VASANT DHAR DISCUSSES KD/DM STRATEGIES 10.07.97)
The volume notes several extended cases dealing with market segmentation, data mining, customer service, financial prediction, and quality control and improvement. There are two versions of the book available, one suited to business people and one for teaching.
Some recent reactions to the book include:
"Intelligent Systems are becoming vital at all levels of management from the CEO to the foreman. Dhar and Stein provide one of the clearest and most accessible treatments to date of the subject."
"Seven Methods effectively bridges the gap between lofty technical explanation and the down-to-earth business application of a brand new world of modeling technologies."
Seven Methods takes a three stage approach to discussing these new technologies. The book is organized around: A framework for analyzing business decision problems and mapping solutions onto them; An intuitive but full discussion of the technologies for data mining and automated decision systems; A series of extensive case studies that show, using the framework, how major organizations have made use of these technologies.
In addition to discussing technologies, Dhar and Stein introduce a unified methodology for analyzing organizations' business problems and evaluating potential solutions. This framework, based on the authors' years of combined experience applying intelligent systems to real business decision problems, encourages business people to think critically about how the strengths and weaknesses of each technique relate to the particular dynamics of an organization and its problems. The authors show not only when a particular modeling method may be useful, but also when its attributes might make it undesirable for a particular problem.
The text does not limit itself to one or a few techniques, but rather views various AI and database techniques as components of a toolbox that, if used correctly, can make organizations dramatically more intelligent. In order to make the material more accessible, the text makes frequent use of rich graphics. The graphical representation of complex concepts are invaluable in elucidating these topics.
To drive home the discussions of modeling techniques and organizational dynamics, the book also provides extended case studies that show in detail how the framework can be applied to analyzing the problems of real organizations. Cases are taken from the experience of firms in a diversity of industries solving an assortment of problems. Firms include: US WEST, Moody's Investors Service, Compaq Computer Corp., LBS Capital Management, NYNEX, Inc., Kaufhof AG, A. C. Neilsen.
UNSUPERVISED ADAPTIVE CLUSTERING FOR DATA PROSPECTING & DATA MINING
by Ben A. Hitt Ph.D., Senior Fellow American Heuristics Corp
Ben A. Hitt, Ph.D. has many years of experience using pattern recognition technologies and intelligent software tools to solve business problems. He has taught thousands of students in the use and principles of advanced software and machine learning technologies. Hitt is Senior Fellow at American Heuristics Corporation (AHC), an advanced software technology company based in Triadelphia, WV. He instructs several short courses at AHC's training division, The Gordian Institute. His latest addition to Gordian's curriculum is an executive level course entitled "Data Mining: Principles and Practice." Hitt was Director of Training for NeuralWare, Inc. in Pittsburgh, PA, and in that role instructed the use of neural networks for Financial Forecasting, Fraud Detection, Process Control and Direct Marketing. He was instrumental in the design and development of ModelMAX, a complete neural network application for the direct marketing industry. He also designed and implemented a nationally recognized detection system for rapid tax refund application fraud. He has recently conducted a detailed and exhaustive survey of commercial data mining products for a major US bank.
Hitt observes: "There was a time, well within the scope living memory, when the dream of market analysts was to have as much data about their prospective customers as they could possibly get. It seemed clear that if one knew all they could about a customer or group customers, the correct marketing approach would become evident. Now, that dream not only has come true, but the mass of data concerning us all has become overwhelming. Indeed, it can be said that the marketer's dream has become something of a nightmare."
DATA MINING COMPLEX PROFILES:
AN INTERVIEW WITH TOM VAN HORN, INFOMODELERS
by Alan Beck, editor in chief
Tom Van Horn joined InfoModelers, Inc. as president and CEO in December 1996 shortly after the company's inception. He has spent the past decade in senior management positions in the information technology and consulting industries. Most recently, Van Horn served as Vice President of International and Specialized Products for Attachmate, and before that as vice president of Corporate Planning and Marketing for Attachmate and Digital Communications Associates (DCA). He also spent five years as a senior management consultant with McKinsey & Company, a premier management consulting firm. Van Horn holds an MBA from the Wharton School, a Master of Arts in International Studies from the University of Pennsylvania, and a BSE in Mechanical and Aerospace Engineering from Princeton University.
InfoModelers is a leading supplier of state-of-the-art visual design tools for database developers and users based on both conceptual and logical modeling technologies. InfoModelers, Inc. began as a division of Asymetrix Corporation and was spun off as a separate company in October 1996 to pioneer the development of database tools incorporating both Object Role Modeling (ORM) and Entity Relationship modeling (ER). ORM uses natural English sentences to express relationships between objects and simplifies modeling by allowing database designers and business users to communicate directly and easily.
ACTION ITEMS
New META Group Study Forecasts 150% Growth in Data Mining Market by Year 2000
META Group, Inc. announced the results of a pioneering study of data mining
imperatives. The study, entitled Data Mining: Trends, Technology, and
Implementation Imperatives, forecasts 150% growth in the data mining market,
from $3.3 billion in 1996 to $8.4 billion in 2000.
FCC Chief of Staff to Partner with KnowledgeBase Marketing
KnowledgeBase Marketing, Inc. (KBM) announced today that Blair Levin, Chief
of Staff under Reed Hundt at the Federal Communications Commission, will
partner with the company to integrate new digital communications technologies
with advanced databases and marketing strategies.
Corvu Corporation Teams with Arbor Software to Integrate
Olap and Business Performance Management Applications
CorVu Corporation, a Minneapolis-based provider of business intelligence
solutions, announced today an Essbase-Ready agreement with Arbor Software
Corporation, a leading provider of enterprise OLAP (OnLine Analytical
Processing) software for management reporting, analysis and planning
applications. The agreement will provide customers with tight integration
between CorVu's integrated Business Intelligence and business performance
management solutions and Arbor Essbase OLAP Server.
D S * INFORMATION
D S * welcomes bylined comments for publication.All comments regarding editorial content should be sent to: dseditor@tgc.com