Optimal Policies and Heuristics To Match Supply With Demand For Online Seasonal Sales
42 Pages Posted: 2 Dec 2018
Date Written: March 28, 2018
We consider an online retailer selling multiple products with random demands for a seasonal sale. The retailer orders the products from a single supplier and stores them at multiple warehouses. Before the season starts, the retailer decides the order quantities of the products and determines their storage quantities to each warehouse subject to its capacity constraint. After the demands are realized, the retailer decides the retrieval quantities from each warehouse to fulfill the demands. The objective is to maximize the retailer's expected profit over the selling season. For the problem with a single demand zone, we find the optimal retrieval policy in closed form. We obtain the optimal storage policy using a non-greedy algorithm that allocates the products to the warehouses iteratively according to each warehouse's updated target stockout probability. Furthermore, the optimal ordering policy is a newsvendor-type policy. The problem becomes intractable when we consider multiple demand zones. We propose three efficient heuristics to solve it. The first heuristic controls the over-stocking risk through virtual demand pooling. The second heuristic is based on virtual capacity allocation that stores the products closer to their target demand zones. The third heuristic is a hybrid of the first two heuristics. A case study with a major fashion online retailer in Asia suggests that all the heuristics achieve a nearly 20% profit improvement over the retailer's current practice. A further numerical study reveals that the hybrid heuristic generally outperforms the first two heuristics and attains a profit within 10% of an upper bound.
Keywords: online retailing, seasonal sales, inventory management, order fulfillment, optimal policies, heuristics
Suggested Citation: Suggested Citation