Article ID: | iaor20121977 |
Volume: | 28 |
Issue: | 2 |
Start Page Number: | 485 |
End Page Number: | 496 |
Publication Date: | Apr 2012 |
Journal: | International Journal of Forecasting |
Authors: | Ord J Keith, Snyder Ralph D, Beaumont Adrian |
Keywords: | simulation: applications, stochastic processes, statistics: distributions, forecasting: applications |
Organizations with large‐scale inventory systems typically have a large proportion of items for which demand is intermittent and low volume. We examine various different approaches to demand forecasting for such products, paying particular attention to the need for inventory planning over a multi‐period lead‐time when the underlying process may be non‐stationary. This emphasis leads to the consideration of prediction distributions for processes with time‐dependent parameters. A wide range of possible distributions could be considered, but we focus upon the Poisson (as a widely used benchmark), the negative binomial (as a popular extension of the Poisson), and a hurdle shifted Poisson (which retains Croston’s notion of a Bernoulli process for the occurrence of