this thesis aims to enable canadian wood pellet producers with the opportunity to offer competitive pricing through optimization of their value chains and supply chains, by employing an operational-level decision support tool (dst). improving the competitiveness of canada’s individual wood pellet manufacturers will ultimately improve canada’s position amidst the rapidly developing global wood pellet market. primary information is used from a case study of industries lacwood (ilw), in hearst, on; a firm that produces wood pellets using residue generated from processing of its primary wood items. the specific objectives of this study are to: 1) determine how to optimize the operations of a wood pellet producer, through a comparison of three different gross margin (gm) optimization models, given uncertain demand conditions. these three models will illustrate why it is important to utilize inventory and a variable production rate, in order to most effectively optimize the gm of a pellet producer, given uncertain consumer demand. 2) produce 100 demand datasets (to satisfy the central limit theorem) for pellet 1 and pellet 2 and run these datasets through each of the three models created for objective 1. compare the gm results of the three models and demonstrate why the operational environment specified in model 2 should be used for gm optimization of wood pellet producers, and will be used for further analysis. 3) generate stochastic demand schedules for pellets by averaging the 100 demand datasets produced for objective 2. use these stochastic demand schedules as the base case demand input values for model 2, along with other standard input values (obtained from ilw). benchmark output values of production, inventory and unfulfilled demand generated from these standard inputs are compared with output values of production, inventory and unfulfilled demand generated from the variable inputs of 11 different scenarios. these comparisons will illustrate how model 2 is a comprehensive dst that the operational-level managers of wood pellet producers may use to achieve optimal gms for the producer, under uncertain demand conditions and with other variable input factors. the results show that the model is most sensitive to fluctuations in demand, supply and inventory holding costs.