Maximizing Revisiting and Purchasing: A Clickstream-Based Approach to Enhance Individual-Level Customer Conversion

Online retailers are increasingly mindful about developing and maintaining a lifetime relationship with customers rather than having a myopic focus on one-time purchases. It is thus critical to ensure that customers continue to revisit a retailer’s website to obtain content and make purchases. The objective of our paper is, therefore, to help retailers maximize the joint likelihood of customers’ revisiting and purchasing. We achieve this joint maximization at the individual customer level. We first build a model that better predicts repeat customer visits compared to existing methods. This model incorporates heterogeneity in individual customer search behavior by distilling her search history into four theory-driven sets of antecedents: (a) choice, (b) information, (c) pricing, and the (d) search environment. We find that, for different customers, the antecedents of conversion work in opposite directions in their influence on revisiting and purchasing. Such opposing influence necessitates balancing between the likelihoods of revisiting and purchasing. Using computationally efficient simulation-based prescriptive analytics, we then propose intervention strategies that rely on the optimal values of certain antecedents that maximize the individual-level joint likelihoods. These strategies provide retailers with insights on personalizing the customer experience based on their search history and presenting customers relevant content in a personalized fashion.