STOKASTİK (R,s,S) ve STOKASTİK (R,S) STOK KONTROL POLİTİKALARININ POLİÜRETAN SEKTÖRÜNDE MARKOV KARAR SÜRECİ YARDIMIYLA KARŞILAŞTIRILMASI

In this study, probabilistic inventory policies are introduced and it has been proved that the (R,s,S) inventory policy based on periodical revision shows Markov chain and Markov decision process characteristics. Thereafter, this policy has been compared with the (R,S) inventory policy which has similar features with the mentioned inventory policy, in terms of costs. The data of an international firm which operates in Turkey in the area of polyurethane, related to the raw material of MDI (methylenediphenyl diisosiyanathe) has been collected and the probabilistic structure of the demand related to this inventory item has been analyzed. The state space has been defined according to the (R,s,S) inventory policy, and the Markov chain has been formed by calculating the probabilities of transition. This policy has been shown as a problem of Markov decision, with the cost function of inventory item, and the expected avarage cost for a time unit has been found. Lastly, same processes have been applied to the (R,S) model which is the actual inventory policy of the mentioned firm, and the costs have been compared.