Getting More Out of Binary Data: Segmenting Markets by Bagged Clustering

There are numerous ways of segmenting a market based on consumer survey data. We introduce bagged clustering as a new exploratory approach in the field of market segmentation research which offers a few major advantages over both hierarchical and partitioning algorithms, especially when dealing with large binary data sets: In the hierarchical step of the procedure the researcher is enabled to inspect if cluster structure exists in the data and gain insight about the number of clusters to extract. The bagged clustering approach is not limited in terms of sample size, nor dimensionality of the data. More stable clustering results are found than with standard partitioning methods (the comparative evaluation is demonstrated for the K-means and the LVQ algorithm). Finally, segment profiles for binary data can be depicted in a more informative way by visualizing bootstrap replications with box plot diagrams. The target audience for this paper thus consists of both academics and practitioners interested in explorative partitioning techniques.