A Recommender System to Nudge Customers in a Capacity Constrained Supply Chain

Abstract

We seek to develop a recommender system that takes into account supply chain constraints regarding the availability of a product while nudging the customers to purchase it. The motivation to study this problem was because a firm faced availability constraints for one of its products but the available quantities still exceeded the current demand. To identify customers to nudge, we develop a Support Vector Machine (SVM) approach to rank order the customers based on their propensity to purchase the product. The underlying notion in our approach is that Type I errors in our classifier are not necessarily problematic but are potential nudging targets. Also, as a consequence, traditional ways of evaluating classifiers (with Type I and Type II errors) are not appropriate. Therefore, we conduct a field experiment to evaluate how well the identified customers are nudged through information and/or couponing. We find that, in terms of the successful nudges, our SVM-based approach performed better than other approaches. The experiment also generated insights about when couponing as opposed to information is more effective when nudging.