ABSTRACT
Indexed by Track Subject
Indexed by Title
Indexed by Author
Data Mining as an Entry or Exit from Spatial Analysis Using GIS or Spatial Query Techniques
Track:  Business Geographics
Author:   Frederick D. Busche

To develop the understanding of the tendency for a customer to exhibit a particular behavior in business situations, many times requires the analyst to use some rather sophisticated techniques for analysis. These techniques include algorithms that use the aspects of artificial intelligence as their basis as well as statistical analysis and the integration of the results into an appropriate spatial representation. These techniques require the expertise of an analyst that is highly skilled mathematically as well as spatially. Unfortunately, this type of analyst is usually not particularly well adapted or experienced with how his analysis relates to the solution of the business problem, and the corollary exists that the typical marketing analyst does not have the mathematical expertise to be able to fully utilize the analytics available. Therefore, GIS sophisticated statistical and/or data mining analytical techniques are not completed by one person but two, one in the back office and one in the front. With the use of the combination of the Web-based, wizard-driven IMforRM software and SDE Spatial Extender from IBM and Esri's ArcView Business Analyst, very sophisticated analyses can be performed with little need for a strong analytical background. This paper discusses the integration of these technologies.

Frederick D. Busche
IBM
3116 Lake Highlands Dr.
Highland Village, TX75077

Telephone: 972-318-1723
Fax: