Volumetric Demand and Set Size Variation

Abstract

Brand managers in packaged goods categories need to understand drivers of both primary and secondary demand (i.e., overall category and brand-specific demand) in order to improve product and pricing decisions. In the presence of variety seeking, primary demand may depend on the composition and size of an assortment (or choice set). Since choice-set size varies between stores, shopping trips and choice contexts, developing models that consider the effect of choice-set size on demand is important for categories with simultaneous demand for varieties (e.g., packaged goods). Larger choice sets not only increase the chance of finding an attractive product, but they also allow consumers to better satisfy their demand for variety. Therefore, we generally expect larger choice sets to result in (at least marginally) higher levels of primary demand. However, the relationship between assortment size and primary demand may heterogenous.Our proposed model builds on volumetric demand models and allows for flexible relationships between choice-set size and primary demand by introducing a location adjustment to the marginal utility of the outside good. The model yields better fit and predictions in the presence of choice-set size variation. Variation in choice set-size is particularly large when rand managers need to predict marketplace demand using choice experiments. While choice experiments involve choices from relatively small choice sets with 2-10 choice alternatives, marketplace offerings typically comprise 100 or more unique products or stock-keeping units. In our empirical application in the chocolate bar category, we find that our model significantly improves predictions of marketplace demand quantities. Our choice experiment comprised tasks with 8 and 18 choice alternatives, while the marketplace scenario consists of over 100 choice alternatives. While our model results in realistic market-level predictions, extant volumetric demand models overpredict demand by a factor of almost two.

Keywords: Choice Models, Demand Analysis, Volumetric Demand, Multiple Discrete Continuous Models, Bayesian Estimation

JEL Classification: M3, C8, C9