Data-driven retail inventory management with backroom effect

Abstract

The backroom effect (BRE) constitutes the handling effort of a replenishment that does not fit on the shelf of a retailer. This effect needs to be included in the decision making of inventory policy parameters as it influences the handling effort, which constitutes a major part of the retailer’s operational cost. We propose a mixed integer linear program to calculate the parameters of a periodic review (s, c, S, nq) policy while considering the BRE. The (s, c, S, nq) policy triggers an order when inventory drops below the reorder point s. Also, an order is triggered whenever the inventory drops below the can-order point c, provided at least one other product’s inventory level is below s and thus ordered. The order then comprises the smallest integer number n of case packs with size q that brings the inventory level to or above S. As retailers face stochastic non-stationary demand, a data-driven approach based on historical data is applied to this joint replenishment problem. The numerical study shows that including the BRE into the optimization can lead to cost savings with a median of 0.96% compared to neglecting its effects. Considering the stochasticity in the decision making, cost improvements with a median of 53.23% have been realized against an approach that only considers average daily demands and a safety stock. The advantage of an (s, c, S, nq) order policy over an (s, S, nq) policy is shown by median savings of 17.99%.