Trading Safety Stock for Service Response Time in Inventory Positioning

Abstract

We study the inventory placement optimization problem, where demand is sensitive to service response time, under the online retailing setting. The main challenge is to achieve the optimal trade-off between revenue benefits from shorter delivery time and inventory operation costs. To predict the effects of modified demand under service response time variations, we introduce a demand prediction and elasticity model to quantify the sensitivity in demand for particular product categories. We also propose a novel data-driven two-stage stochastic programming approach complementing the demand prediction and elasticity model, which optimally trades safety stock for service response time. We then illustrate the efficiency of our approach through data provided by an e-commerce retailer in North America. Our approach offers supply chain managers a general-purpose decision support tool that optimizes the inventory network to generate recommended stocking levels for stores, distribution centers and warehouses on a daily basis.

Keywords: sales forecast, risk pooling, service quality, supply chain network, online retailing

JEL Classification: C52, C61, P46