Inventory replenishment in multi-stage production setting under stochastic demand: a review

Abstract

Inventory management is central to production planning and control particularly in multi-stage production environment where production output is stochastic and customer demand is also stochastic. Surplus inventory ties down money and stock-out situation result in loss of value and goodwill. Therefore, it is necessary determine optimal inventory policies for different manufacturing scenarios to maintain a balance between safety stock inventory and customer demand satisfaction at all time. Consequently, this review attempts to identify and document the underlying trends and most recent methods of inventory replenishment under stochastic demand with emphasis on multi-stage production setting. Prominent in literature among the models used to treat inventory problem in stochastic demand situation is “Approximation by Probabilistic Distribution”. Other models used include, Genetic Algorithm (GA), Just-in-time with Kanban simulation, Markov Process Decision, Fuzzy Inventory Model, Multi-stage inventory-queue model and Demand forecasting among others. It appears that there exist only approximate solutions than exact solutions in solving stochastic demand inventory problem suggesting that there is need for more work to be done in the area toward achieving exact solutions to the problem than approximation.