Abstract
This paper examines the crude oil procurement practices of Chinese oil refineries to suggest improved procurement policies that can reduce the cost associated with fluctuating oil prices in the international spot market. In the industrial environment, the purchase price of crude oil is based on the spot price at the time of delivery rather than that at the time of ordering. Therefore, the purpose of this paper is to develop a procurement model that factors in the spot prices at both the time of ordering and the time of delivery so that the total procurement cost can be minimised over the planning horizon. First, the shortcomings of the current procurement policy of a typical Chinese refinery are presented. A model to address these shortcomings is then developed and embellished by incorporating market information dynamics through Bayesian learning. The effectiveness of the proposed models is compared with the current practice using the historical spot price data of crude oil from two representative spot markets; this comparison verifies that the model with Bayesian sampling performs well empirically and can result in considerable cost savings.
Acknowledgements
This study is supported in part by the National Natural Science Foundation of China (Grant No. 71071084). The authors thank H.S. Deng, X.F. Li, A.B. Pang and G.P. Xiao from the China Petroleum & Chemical Corporation for the detailed information on refinery procurement operations. The authors also thank Prof. S. M. Huang from Tsinghua University for his valuable comments and coordination over the research project.