The paper considers the problem of modelling the lead-time demand for the multiple slow-moving inventory items with low consumption and short requests history. The Bayesian approach is used to overcome the problems with the past demand data: the beta-binomial model is employed to predict the lead-time demand probability distribution for each item. Further, an extension of this model is developed that allows accounting for the prior information regarding the maximum expected probability of demand per period. Parameter estimation and Bayesian forecasting routines are derived for the new model. The practical significance of the obtained results is supported by the simulation study.