Reducing the optimal to a useful number of clusters for model-based clustering

Abstract

Market segmentation is the process in marketing of grouping customers into smaller subgroups, according to a certain segmentation basis. Market segmentation is only practically useful if the effectiveness and profitability of marketing activities are influenced substantially by discerning separate homogeneous groups of customers. Using six criteria, described by Wedel and Kamakura, the effectiveness and profitability of market segmentation can be determined. However, using model-based clustering techniques to group customers, the statistically optimal solution often contains too many clusters for the intended marketing purposes. Using the six criteria of good market segmentation, an information criterion and two conjectures, describing the geometry of model-based clustering models, presented by Hoijtink and Notenboom, a procedure to reduce the statistically optimal number of clusters to a smaller number, suited for the intended marketing purposes, is presented. © 2010 Macmillan Publishers Ltd.