Modeling the Transshipment Decision in Retail Networks with Periodic Replenishments

We consider the transshipment decision in a retail network with periodic replenishments. We propose a Markov decision process model that allows transshipments to occur throughout the period, both in response to, and in anticipation of, stockouts. We propose approximate solution methods based on simple calibrations of individual locations. Numerical experiments show strong performance of the proposed methods compared to standard policies.