This dissertation, "Procurement Risk Management Using Commodity Futures: a Multistage Stochastic Programming Approach" by Yihua, Xu, 許意華, was obtained from The University of Hong Kong (Pokfulam, Hong Kong) and is being sold pursuant to Creative Commons: Attribution 3.0 Hong Kong License. The content of this dissertation has not been altered in any way. We have altered the formatting in order to facilitate the ease of printing and reading of the dissertation. All rights not granted by the above license are retained by the author. Abstract: ABSTRACT This study addresses the procurement risks that arise from variations in customer demand and fluctuations in the prices of material to be purchased, and seeks ways to effectively manage these risks. Procurement is prone to risks due to the uncertainties in, for example, demand, price and delivery. The effective management of these risks is hence a critical provision within the framework of procurement planning. However, what generally interests a procurement manager, when attempting to match closely product supply with customer demand, is the lowest cost that could possibly be attained. This mindset is found to concur with traditional models for procurement planning, which tend also to focus on cost minimization or the maximization of profit. With the potential risks largely ignored, such traditional models are clearly inadequate in the dynamic and precarious environment in which procurement is to be performed. This study describes a procurement planning approach that takes into account the risks arising from the fluctuations in procurement prices and customer demand volatility during a procurement undertaking. From the perspective of risk management, procurement is concerned with minimizing the downside risk exposure by means of hedging the associated risks so as to avoid possible losses. The specific risk hedging method developed in this study is based on the commodities and derivatives markets, which have grown rapidly and flourished in the age of e-commerce. This method is based on the static financial risk-hedging models that deal with a fixed hedged quantity. However, in making operational decisions in which the purchased quantity fluctuates due to customer demand, hedging has to be performed dynamically and this forms a significant extension to the available models. To allow and support operational procurement decision making as well as financial risk hedging in the presence of commodity markets, an integrated procurement risk management framework is developed. The development of this framework involves three major research issues (i) the establishment of a quantitative procurement risk management framework; (ii) the modelling of the stochastic behaviour of commodity prices and customer demand; and (iii) in II matching the two stochastic quantities mentioned above, the modelling of the procurement planning and financial risk hedging problem, jointly represented as a multistage stochastic program. The solutions obtained from this stochastic programming model can be evaluated according to the specified profit/risk profiles of a decision maker. To model the stochastic behaviour of commodity prices, the Gibson-Schwartz two-factor model and the Schwartz-Smith two-factor model are employed for storable commodities and non-storable commodities respectively. State-space form models and Kalman filtering are used to estimate the parameters of the empirical price models based on historical commodity price data. Two commodities are studied in this research. One is copper which is storable, and the other is electricity which is non-storable. Using the empirical price models, scenarios can be generated for stochastic program optimization. Numerical experiments are carried out to demonstrate the benefit that could be gained from the use of the integrated procurement risk management approach developed in this study. It is found that, when compared with pure operational pla