Application of multi-steps forecasting for restraining the bullwhip effect and improving inventory performance under autoregressive demand

Recent research suggests that the bullwhip effect, or increasing variability of inventory replenishment orders as one moves up a supply chain, illustrates inventory management inefficiencies. This paper quantifies the bullwhip effect in the case of serially correlated external demand, if autoregressive models are applied to obtain multiple steps demand forecasts. A materials requirements planning (MRP) based inventory management approach is proposed to reduce the order variance. Simulation modeling is used to investigate the impact of the forecasting method selection on the bullwhip effect and inventory performance for the most downstream supply chain unit. The MRP based approach is shown to reduce magnitude of the bullwhip effect while providing the inventory performance comparable to that of a traditional order-up approach. The application of autoregressive models compares favorably to other forecasting methods considered according to both the bullwhip effect and inventory performance criteria.