A one-time excess inventory disposal decision under stochastic and price dependent demand

Abstract

This thesis studies a one-time excess inventory disposal problem where the demand during the disposal period (DDDP) is stochastic and its distribution depends on the disposal price. More specifically, this thesis considers a periodic-review stochastic inventory system that has been operated under a policy different from the one that is to be implemented in the future. Such a situation may arise as a result of changes in the model assumptions that lead to the implementation of a different policy. Before the new policy is implemented, there may be some units on hand that exceed the optimal order-up-to level. Consequently, the inventory manager needs to evaluate a one-time inventory disposal decision immediately before the new/modified policy replaces the policy in use. In the thesis, the situations and applications of the problem are discussed in detail, and a model applicable for all of the demand patterns is derived and analyzed. Four special models studied include the cases where the DDDP and the regular demand are assumed to be (i) exponential distribution and exponential distribution, (ii) exponential distribution and uniform distribution, (iii) uniform distribution and exponential distribution, and (iv) uniform distribution and uniform distribution, respectively. The second and fourth models do not have closed forms but they can be solved numerically. The first and third models have compact closed forms and thus the mathematical properties of the objective function are presented and explanations associated with the particular problem are provided. Based on the analytical results, the models are simplified, and the programs are developed to compute optimal solutions. Finally, some numerical examples are demonstrated for further elaboration.