Single Period Inventory Models for Products whose Demand Follows Compound Distributions

Abstract

Up to this point, the Single Period Inventory models developed have focused on a product whose demand distribution in a single period is some simple classical distribution like the normal distribution, log-normal distribution, etc. These models are silent on the fact that the number of customers visiting a retail outlet to demand the product is a random variable with some probability distribution, typically the Poison distribution (for this project). In this thesis, a model that assumes that the number of customers visiting a retail outlet during a single period is Poison distributed is developed; each customer's demand for the product in turn is assumed to be a random variable X that follows some known distribution D ( è ), where è is the parametric vector for the distribution.