ESSAYS ON MULTICATEGORY DEPENDENCE MODELS OF CONSUMER CHOICE

Abstract

This research concentrates on understanding the dynamic choice behavior of households using econometric models; specifically the influence of promotional campaigns and cross-category dependencies on purchase incidence outcomes.

In the first section, we empirically estimate the expected basket-level demand effects and, therefore, the expected store profit effects of three different types of retailer targeted coupon campaigns used by a national supermarket retail chain. The three types of campaigns differ in terms of household-level personalization. One campaign employs a one-to-one approach by targeting a set of selected households with a unique bundle of coupons personalized to that household’s preferences (high personalization). Another campaign promotes a bundle of brands around a theme (i.e., back-to-school) relevant to the household (medium personalization). The third type provides a limited number of coupons for one brand in a single category relevant to the consumer (low personalization).

We build and estimate an econometric model of a household’s contemporaneous purchase incidence outcomes in 28 product categories, together with a household-level store choice model. In terms of relative efficacy, we find that theme-based coupons (medium personalization) lead to more incremental expected retailer profits for a small number of coupons (e.g. 5-7) when dropped in a single category (e.g. fresh vegetables). However, due to higher degrees of freedom, one-to-one coupons (high personalization) generate an even greater expected retailer profit when bundling coupons across a large number of categories (e.g. 20).

In the second section, we attempt to advance the literature on multi-category demand models by modeling cross-category dependencies in households’ purchase incidence outcomes. We propose an extended version of the Multivariate Logit Model of Russell and Peterson (2000) that enables the estimation of higher-order cross-category dependencies. We document both positive and negative higher order cross-category dependences in consumer demand. This systematic demand structure analysis allowed us to find a counterintuitive bundle of hot dogs, non-cola beverages and toilet paper which generated the highest expect revenues.

The results from our studies provide insights to retailers about the value of investing in more personalized promotional efforts, and with a detailed cross category glimpse of where such value is gained.