MODELING THE EVOLUTION OF DEMAND FORECASTS WITH APPLICATION TO SAFETYSTOCK ANALYSIS IN PRODUCTION DISTRIBUTION-SYSTEMS

In this paper, we propose a general probabilistic model for modeling t he evolution of demand forecasts, referred to as the Martingale Model of Forecast Evolution (MNFE). We combine the MMFE with a linear progra mming model of production and distribution planning implemented in a r olling horizon fashion. The resulting simulation methodology is used t o analyze safety stock levels for a multi-product/multi-plant producti on/distribution system with seasonal stochastic demand. In the context of this application we demonstrate the importance of good forecasting .