Holding Inventory with Stochastically MeanReverting Purchase Price

Peter Berling Địa chỉ email này đã được bảo vệ từ spam bots, bạn cần kích hoạt Javascript để xem nó.

Department of Industrial Management and Logistics Lund Universit,y, P.O. Box 118 SE-221 00 LUND, SWEDEN

IM 23

Abstract

This paper serves a dual purpose, 1. to improve the understanding of how to measure the inventory carrying charge, 2. to develop a simple heuristic for inventory control when the purchase price is stochastic.

The single-item inventory problem with a fix set-up cost is considered. Demand is stationary and deterministic and there are no shortages.

The stochastic purchase price follows the  mean-reverting Ornstein-Uhlenbeck process that frequently appears in the Financial Economics literature.

The out-of-pocket holding cost is sufficiently high to preclude price speculation. The optimal policy is derived and compared with heuristics based on the EOQ formula, the Silver Meal and the Part Period algorithm.

The heuristic idea is to add the expected price decrease per period to the base holding cost coefficient, which is the sum of the out-of-pocket holding cost and the opportunity cost of capital evaluated at the risk-free interest rate.

Simulation tests suggest that the EOQ formula should work excellently when the average price change is estimated over 1/3 to 2/3 of the order cycle. Given future prices, an iterative procedure for finding this order quantity is presented. For items quoted on commodity markets, expected future prices should be estimated by the quoted forward prices.