Usage of Decision Aids and the Evolution of Online Purchase Behavior

Abstract

This study investigates how prior usage experience with various decision aids available in an Internet shopping environment contributes to online purchase behavior evolution. Four types of decision aids are examined: those for (1) nutritional needs, (2) brand preference, (3) economic needs, and (4) personalized shopping lists. We construct and estimate nonhomogeneous hidden Markov models of store- and category-level purchase decisions, in which parameters vary over time across hidden states as driven by usage experience with different decision aids. We find that consumers evolve through distinct behavioral states over time, and the evolution is attributable to their prior usage experience with various decision aids. Moreover, the impact varies by the specific decision aid, behavioral state, and category characteristics. In addition, consumers gravitate toward habitual decision processes in online grocery stores, and their average price and promotion sensitivities increase first and then decrease but the level of heterogeneity rises continuously. We identify beneficial versus potentially undesirable decision aids and demonstrate how the proposed research method can help online retailers improve their store environments, design customized promotions, and quantify the payoffs of these strategies.

Keywords: Internet marketing; shopper marketing; interactive decision aids; customized promotions; store environment; retail management; e-commerce; decision heuristics; click-stream data; Bayesian statistics; hidden Markov model