Dynamic Inventory Planning with Unknown Costs and Stochastic Demand

Generally, ordering policies are done by two methods: fix order quantity (foq) and fix order period (fop). the mentioned methods are static. it means that the quantity of ordering or the procedure of ordering is fixed throughout time horizon, while in real environments, demand may vary in any period, i.e., dynamic; it may be considered as uncertainty. when demand is variable in any period, the traditional static ordering policies with fixed reorder points cannot be efficient. on the other hand, sometimes, in real environments, some costs such as holding cost and ordering cost may not be well-known or precise. therefore, using the costbased inventory models may not be helpful. in this paper, a model is developed which can be used in the cases of stochastic and irregular demands, also unknown as costs. indeed, in these cases, re-order point can be dynamic. also, some attributes consisting of expected positive inventory level, expected negative inventory level, and inventory confidence level are considered as objective functions, instead of the objective function of total inventory cost. a numerical example is also presented for more explanation.