Diamonds in the Rough: Leveraging Click Data to Spotlight Underrated Products

Abstract

Problem Definition. Inspired by a data set from the Chinese retailer JD.com, we study the click and purchase behavior of customers in an online retail setting by employing a structural estimation approach.

Methodology/Results. We use a dynamic discrete choice framework to model the customer’s optimal search strategy, and propose a novel value function approximation scheme to address the curse of dimensionality and estimate the model efficiently. By combining the click and order data, our proposed structural framework allows us to disentangle and separately estimate the attractiveness of a product before and after the click. This, in turn, allows us to identify underrated products which we call diamonds in the rough: these are products that have low pre-click but high post-click attractiveness; thus, even though such products have a low chance of being clicked, they have a high chance of being purchased, if clicked. The online retailer can increase the revenue by bringing such products into the spotlight to entice customers to click on them.

Managerial Implications. The proposed framework provides an online retailer with new tools and insights to better manage the product assortment based on customer click and purchase behavior. Through simulation studies, we illustrate how our model can be operationalized and used for improving assortment decisions by accounting for the unobserved product utilities. In particular, we show that the optimal assortments under our model increase the expected revenue by 14% compared to the actual assortments displayed by JD.com, and by 37% compared to an MNL model that only focuses on the observed product utilities.

Keywords: Online Retailing, Consumer Search Model, Structural Estimation, Click Data, Personalization