A Review of Unquestioned Standards in Using Cluster Analysis for Data-Driven Market Segmentation

Clustering is a highly popular and widely used tool for identifying or constructing databased market segments. Over decades of applying cluster analytical procedures for the purpose of searching for homogeneous subgroups among consumers, questionable standards of utilization have emerged, e.g. the non-explorative manner in which results from cluster analytic procedures are reported, the black-box approach ignoring crucial parameters of the algorithms applied or the lack of harmonization of methodology chosen and data conditions. The purpose of this study is threefold: (1) to investigate whether and which standards of application of cluster analysis have emerged in the academic marketing literature, (2) to compare these standards of application to methodological knowledge about clustering procedures and (3) suggest changes in clustering habits. These goals are achieved by systematically reviewing 243 data-driven segmentation studies that apply cluster analysis for partitioning purposes.