Accommodating heterogeneity in brand loyalty estimation: application to the U.S. beer retail market

Abstract

The assessment of consumer behavior in brand-choice models may be greatly influenced by accurately modeling and evaluating a brand-loyalty parameter. The most well-known approaches for estimating brand loyalty employ a household’s past purchase data and account for habit formation with a single smoothing parameter that indicates the weight assigned to households’ current decisions versus their distant shopping history. In this study, we present a method for estimating time-varying smoothing parameters for heterogeneous households. We estimate smoothing parameters for American households from 2014 to 2017 using Nielsen Homescan data for the US beer retail market. Using this more flexible method, we discover that the smoothing parameter varies significantly among households and time frames (for the same households). We next include a brand-loyalty index based on this approach into a brand-choice model of the American beer retail market, demonstrating that this new method improves estimation results.