Mouna Mezghani Taicir Loukil Belaid Aouni MANAGER PREFERENCES MODELLING FOR STOCHASTIC AGGREGATE PLANNING Abstract In the Aggregate Production Planning (APP) the manager considers simultaneously conflicting objectives such as total cost, inventories level, workforce fluctuation, and utilization level of the physical facility and equipment. The goals associated with these objectives may be uncertain in nature. The aim of this paper is to develop a Goal Programming (GP) model where the goals and the right-hand sides of constraints are random and normally distributed. The concept of satisfaction functions will be used for modeling the uncertainty as well as to explicitly integrate the manager preferences. The proposed model is applied to APP problem to generate the most satisfying aggregate plan. Keywords Aggregate Production Planning; Goal Programming; satisfaction functions. Introduction Aggregate Production Planning (APP) deals with matching capacity to forecasted demand. The APP aims to set overall production levels for each family of products to meet fluctuating or uncertain demand in the medium term to set decisions and policies concerning hiring, firing, overtime, backorders, subcontracting and inventory level, and thus determining the appropriate resources that will be used. The APP is one of the most important functions in production and operations management. Traditionally, the objective of the APP is either to maximize profit or minimize costs and is formulated as a single objective function in linear programming [Hanssmann and Hess, 1960; Bowman, 1956]. Many researchers and practitioners are increasingly aware of the presence of multiple objectives