A combined approach for segment-specific market basket analysis
Market baskets arise from consumers shopping trips and include items from multiple categories that are frequentlychosen interdependently from each other. Explanatory models of multicategory choice behavior explicitly allow for suchcategory purchase dependencies. They typically estimate own and across-category effects of marketing-mix variables onpurchase incidences for a predefined set of product categories. Because of analytical restrictions, however, multicategorychoice models can only handle a small number of categories. Hence, for large retail assortments, the issue emerges of howto determine the composition of shopping baskets with a meaningful selection of categories. Traditionally, this is resolvedby managerial intuition. In this article, we combine multicategory choice models with a data-driven approach for basketselection. The proposed procedure also accounts for customer heterogeneity and thus can serve as a viable tool for designingtarget marketing programs. A data compression step first derives a set of basket prototypes which are representative forclasses of market baskets with internally more distinctive (complementary) cross-category interdependencies and areresponsible for the segmentation of households. In a second step, segment-specific cross-category effects are estimatedfor suitably selected categories using a multivariate logistic modeling framework. In an empirical illustration, significantdifferences in cross-effects and price elasticities can be shown both across segments and compared to the aggregate model.