Design for postponement: A comprehensive characterization of its benefits under unknown demand distributions

Recent papers have developed analytical models to explain and quantify the benefits of delayed differentiation and quick response programs. These mode ls assume that while demands in each period are random, they are independen t across time and their distribution is perfectly known, i.e., sales foreca sts do. not need to be updated as time progresses. In this paper, we charac terize these benefits in more general settings, where parameters of the dem and distributions fail to be known with accuracy or where consecutive deman ds are correlated. Here it is necessary to revise estimates of the paramete rs of the demand distributions on the basis of observed demand data. we ana lyze these systems in a Bayesian framework, assuming that our initial infor mation about the parameters of the demand distributions is characterized vi a prior distributions. We also characterize the structure of close-to-optim al ordering rules in these systems, for a variety of types of order cost fu nctions.