About AMA

Executive Summary
Internet retailers can attract consumers over a wide geographical area. This raises important questions about how demand at Internet retailers evolves not only through time but also over space. Previous literature demonstrates the role of imitation in generating demand; all else being equal, imitation among agents is more likely when they are geographically proximate or “similar” along dimensions such as sociodemographics, culture, interests, and preferences. Building on this stream of research, the authors allow imitation behavior to be reflected both in geographic proximity and in demographic similarity. Then, they examine how the imitation behavior among consumers drives demand at Internet retailers and, ultimately, what firms might do to expedite the process of demand evolution.

To this end, the authors develop a Bayesian spatiotemporal model of demand with two imitation effects: (1) the proximity effect and (2) the similarity effect. Because these imitation effects can be time varying, the authors specify their dynamics using a polynomial smoother embedded within the Bayesian framework, and they obtain the time-varying estimates for these imitation variables, along with other locally defined covariates. They apply the model to new buyers at Netgrocer.com and calibrated it on 45 months of data that span all 1459 zip codes in Pennsylvania.

The authors find that the proximity effect is especially strong in the early phases of demand evolution, whereas the similarity effect becomes more important with time. Over time, new buyers are increasingly likely to emerge from new zip codes beyond the “core set” of zip codes that produce the early new buyers, and thus spatial concentration declines. The managerial implications of this finding are explored through a hypothetical “seeding” experiment. The best strategy for choosing zip codes in which to seed new buyers automatically adjusts the initial focus on populous regions with acquisition of more remote and dispersed customers over time.

Internet retailers6 in their infancy should probably focus initially on populous metropolitan areas, but over time they should incorporate the similarity effect as local concentration of demand declines and a spatially expanded customer base becomes more important to growth. Serving many small pools of somewhat similar buyers, who are spatially distant from each other, can be important to an Internet retailer as the relative contribution of these buyers to sales increases over time. The finding on the importance of the sales distribution over obscure regions mirrors the importance of the sales distribution over obscure products in the long tail. Here the benefit comes primarily through the ability to sell in essentially unlimited local markets rather than an unlimited product assortment.

Biography
Jeonghye Choi is Assistant Professor of Marketing at Yonsei University. She received her PhD in Marketing from the Wharton School at the University of Pennsylvania. Her research focuses on interdependency among individual consumers and local markets, roles of search and word of mouth in online retail settings, online–offline channel substitution, and spatiotemporal diffusion of online retailers.

Sam K. Hui is Assistant Professor of Marketing in the Stern School of Business at New York University. His main research interests are models for shopping paths, entertainment industry (e.g., movies, DVDs, casinos), spatiotemporal diffusion, and concept maps analyses.

David R. Bell is Associate Professor at the Wharton School, University of Pennsylvania. His research focuses on individual and interdependent choice behavior, with applications in retail settings, and appears in various marketing journals, including Journal of Marketing Research, Journal of Consumer Research, Management Science, Marketing Science, Quantitative Marketing and Economics, Journal of Retailing, and Marketing Letters. David holds an MCom in Marketing and International Business from University of Auckland, an MS in Statistics from Stanford University, and a PhD in Business from Stanford University.

Member Comments (0):

To rate or comment on articles, you must be a logged in AMA member. Click here to join