A General Choice Model for Bundles with Multiple-Category Products: Application to Market Segmentation and Optimal Pricing for Bundles

Abstract

The attribute-based approach to study customer choices cannot deal with bundles of heterogeneous components, which are usually drawn from different product categories. The authors develop the comparability-based balance model, which is a unified framework for modeling bundle choices. The model can be employed for any bundle, regardless of the heterogeneity of bundle components, under a pure bundling strategy. The conjoint model and balance model are special cases of the general model. The authors use mixture distributions in a hierarchical Bayesian framework to incorporate consumer heterogeneity in a more flexible manner than the extant approaches such as latent-class and random-coefficient models. The empirical tests of the model show that most attribute effects are significant and consistent with the model's predictions. The model is superior to those that do not consider the issues of comparability of attributes, latent-class structure, and heterogeneity among respondents. The authors show how the model can be used to find market segments for bundles with heterogeneous products in multiple product categories, to estimate individual reservation prices for bundles, and to determine the optimal bundle prices for different market segments.