关键词: 双重不确定信息, 双采购源, 两周期需求, 贝叶斯信息更新

Abstract:

In this paper, we investigate the retailer's dual sourcing policy of multi-stage demand. We assume that the demand of the product has two level uncertainty, i.e., the uncertainty of the product requirements and distribution parameters. Models are constructed for one procurement opportunity and dual sourcing procurement respectively. In order to compare the impact of Bayesian information updating, we compare the optimal policies of three different cases. The result shows that Bayesian information updating can help retailers grasp the changes of market and gain more profits. We also discuss the influences of each parameter on the retailer's optimal policy and the value of demand forecast updating. It is found that the value of demand forecast updating is positively related to the uncertainty of the distribution parameters and negatively related to the uncertainty of the product requirements. Another finding is that when the purchasing cost in the second period is not too high, or both the purchasing cost in the second period and the sum of the purchasing cost and inventory cost in the first period are at similar levels, the demand forecast updating is valuable.

Key words: bi-level uncertain demand information, two ordering opportunities, multi-stage demand, Bayesian information updating