Most techniques for inventory management assume that the parameters of the corresponding model for demand forecasting are known with certainty. However in practice, parameters are estimated from information that may come from available data and/or expert judgment. In this article, we present a Bayesian framework that is appropriate to incorporate the uncertainty on the parameters of the model that is used for demand forecasting, and we show how the main performance measures that are required for inventory management (service levels and reorder points) can be estimated.