Quantifying the value of information and information sharing in a supply chain

Heung-Kyu Kim, Purdue University

Abstract

We consider two inventory models to study the value of information and information sharing in a supply chain. We first consider the inventory problem faced by a retailer who does not know the exact distribution of demand, and must thus use some observed demand data to forecast demand. We present an extension of the basic newsvendor model that allows us to quantify the value of the observed demand data and the impact of forecast updating on expected costs at the retailer. This model can also be used to quantify the value of information and information sharing for a simple supply chain in which both the retailer and the manufacturer must forecast demand. Next, we consider the impact of incorrect or naive assumptions about the demand process, and information sharing with some delay, on costs in a simple supply chain. We present a mathematical model that allows us to quantify the cost incurred by each participant in the supply chain under information sharing with some delay vs. no information sharing and correct vs. incorrect (or naïve) assumptions about the demand distribution. Finally, we consider some extensions of these basic models to address multiple retailers, alternative order-up-to inventory policies that trade off the bullwhip effect at the upstream stage against cost minimization at the stage under consideration, and centralized multi-echelon inventory policies.

Degree

Ph.D.

Advisors

Ryan, Purdue University.

Subject Area

Industrial engineering

COinS