Three Essays On Decision Making In Operations Management

Author : Ting Luo (Ph. D.)
Publisher :
ISBN 13 :
Total Pages : pages
Book Rating : 4.:/5 (18 download)

DOWNLOAD NOW!

Download or read book Three Essays in Operations Management written by Ting Luo (Ph. D.) and published by . This book was released on 2016 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: This dissertation focuses on the role of dynamic information and incentives in service and manufacturing operations, where the information for decision making is often dispersed, privately held, and evolving dynamically over time. Below we briefly summarize each problem: In the second chapter, we examine how managers in intermodal marketing companies should use dynamic forecasting to coordinate daily operations, enhance efficiency and improve profitability. The problem arises from our collaboration with Hub Groups, the largest U.S. intermodal company. The study characterizes the effects of dynamic forecasting on profitability and policy choice. When it comes to profitability, dynamic forecasting reduces the need for carrying large stockpiles for an extended time, thereby saving on holding costs. It also ensures swift stock buildups for imminent shortages. With policy choice, dynamic forecasting guides policy formulation. As a testament, a variant of our model has been implemented by Hub Groups and delivered substantial performance improvement. In the third chapter, we examine the critical role of advance supply signals—such as suppliers financial health and production viability—in dynamic supply risk management. The firm operates a multi-class demand, multi-supplier inventory system. The sales are discretionary and suppliers are susceptible to both systematic and forecasting risks. We build a hierarchical Markov model to capture both the volatility and variability of advance supply signals, and use it to coordinate replenishment and selling. We show that the optimal procurement is driven by supply diversification and intertemporal substitution, the optimal selling is driven by customer segmentation and intertemporal rationing, and that they should be synchronized with dynamic forecast for adaptive and resilient risk mitigation. Interestingly, we find that demand heterogeneity may reduce the value of discretionary selling, that meanvalue-based forecast may outperform stationary-distribution-based forecast, and that taking more information into account need to always be better. This work is among the first to analyze the interplay of forecasting, procurement, and selling, thereby identifying the coordination role of signal-based forecasting in supply risk management. In the fourth chapter, we consider how dynamic information asymmetry and stochastic learning shape the contract design in long-term outsourcing. In this two-period problem, the supplier can reduce production costs through stochastic learning, but the learning outcome is his private information. This complicates the buyer’s contracting problem substantially, as now he must adjust price and production for both periods, properly balancing the benefit of learning and the cost of motivating the supplier. We demonstrate that the buyer may downward distort production in either period for the low type supplier, and not distort the production in either period for the high type supplier. This is driven by the interplay of the learning rate, information asymmetry, and intertemporal consideration. Thus, we can rationalize many outsourcing practices that cannot be explained by the existing adverse selection literature, where downward distortion is the norm. Moreover, the static long-term contract can only substitute the dynamic long-term contract when the learning rate is not substantial.