Bayesian Network Forecasting of Key Material Supply in Uncertain Environment

Supply chain increase in complexity, forecast of key material supply has become indispensable to effective operations management in global market. Unfortunately, rapid technological changes and an abundance of product configurations mean that the supply for key material is frequently volatile and hard to forecast. The paper describes a Bayesian Network (BN) model which was embodies a parametric description of some factors in key material supply forecasting, such as life cycle, oil price, salary level, BOM, supply-demand relationship, and seasonal fluctuations, etc. Furthermore, the model is able to pool supply patterns with little or no supply history data. Finally, the paper discusses the problem addressed by the model, and then analyses its forecast performance.