Cluster Analysis of Marketing Data Examining On-line Shopping Orientation: A Comparison of K-Means and Rough Clustering Approaches
Kevin E. Voges (Griffith University, Australia), Nigel K.L. Pope (Griffith University, Australia) and Mark R. Brown (Griffith University, Australia)
Copyright: © 2002
Cluster analysis is a common market segmentation technique, usually using k-means clustering. Techniques based on developments in computational intelligence are increasingly being used. One such technique is the theory of rough sets. However, previous applications have used rough sets techniques in classification problems, where prior group membership is known. This chapter introduces rough clustering, a technique based on a simple extension of rough sets theory to cluster analysis, and applicable where group membership is unknown. Rough clustering solutions allow multiple cluster membership of objects. The technique is demonstrated through the analysis of a data set containing scores on psychographic variables, obtained from a survey of shopping orientation and Web purchase intentions. The analysis compares k-means and rough clustering approaches. It is suggested that rough clustering can be considered to be extracting concepts from the data. These concepts can be valuable to marketers attempting to identify different segments of consumers.