Ordering and Ranking Products for an Online Retailer

Abstract

In e-commerce, product ranking and display affect customer choices and sales as items placed in top positions receive significantly more clicks than items placed at the bottom. For retailers who sell items from the inventory they have purchased and owned, product ranking has a profound impact on future demand as well as the amount of inventory to be ordered before the selling season starts. However, in many cases, inventory ordering and product ranking decisions are made separately at different times by different functional departments with little or no coordination. One of the main challenges is that the complexity of product ranking problem grows exponentially as the number of products on display increases.

In this paper, we show that it is important to consider inventory ordering and product ranking decisions as a joint problem, and study how this can be done. We investigate three widely-used rank-choice models from the literature and show that we can develop tractable solution methods through approximating the choice behavior with a simpler model in a variety of ordering-and-ranking problems. In a problem where inventories are ordered and a stationary ranking is used throughout the season, we show that the joint ordering-and-ranking problem can be reformulated into an easier assignment problem built on a sequence of newsvendor solutions, leading to a polynomial algorithm. We then consider a problem where product rankings can be dynamically updated, and show that the above algorithm and its variant are asymptotically optimal. We also study a cold-start version of the problem where a retailer has to learn demand parameters from pre-order sales. Building on our analytic results, we propose a two-phase online learning algorithm with a theoretical performance guarantee. Using computational experiments, we show that considering inventory and ranking jointly results in significant profit gain, and furthermore, our algorithms can solve problems with a large number of products and generate high-quality solutions when it is not possible to get an optimal solution efficiently with the exact demand model.

Keywords: product ranking, inventory ordering, online learning, e-commerce