2016 INFORMS Annual Meeting Program

MB35

INFORMS Nashville – 2016

MB35 205A-MCC

2 - Analytical And Empirical Study Of Complementarities In An Online Advertising Supply Chain And Their Impact On Optimal Operating Policies And Profits Changseung Yoo, PhD Student, The University of Texas at Austin, Austin, TX, United States, changseung.yoo@phd.mccombs.utexas.edu, Anitesh Barua, Genaro Gutierrez We examine channel structures and pricing models in an online advertising supply chain using a proprietary dataset. We develop analytic as well as structural econometric models that enable us to and quantify synergy effects between them. While the extant literature emphasizes choosing between pricing models, we show that using multiple models in concert yields higher overall profitability due to strategic complementarities among the pricing schemes. We then explore the operating implications of the complementarities and their impact on profits and supply chain efficiency, and devise information/profit sharing contracts that boost the supply chain profit towards the benchmark scenario. 3 - Supplier Centrality And Auditing Priority In Socially Responsible Supply Chains Jiayu Chen, The University of Texas at Dallas, Richardson, TX, United States, jxc144030@utdallas.edu, Anyan Qi, Milind Dawande We consider a supply network where buying firms’ brand may be damaged by sourcing from suppliers who fail to comply with socially responsible standards. To mitigate the risk, firms may audit their suppliers. We derive firms’ equilibrium auditing strategy and propose approaches to mitigate the inefficiency. 4 - Dynamic Coordination In A Supply Chain With Production Capacity Uncertainty Zhongjie Ma, Purdue University, 403 W State Street, West Lafayette, IN, 47906, United States, ma220@purdue.edu, Qi Feng, J. George Shanthikumar We study the effect of upstream supply capacity uncertainty on the inventory decisions in a two-stage supply chain from both centralized and decentralized perspectives. Extending the notion of stochastic linearity and directional concave order, we show that the centralized problem is concave via transformation. This observation allows us to extend the well-known Clark-Scarf decomposition results to the multi-echelon inventory system with random capacity. Furthermore, we discuss the mechanism to dynamically coordinate the supplier’s and retailer’s decisions when they each possess private information. MB37 205C-MCC Socially and Environmentally Responsible Operations Management Sponsored: Manufacturing & Service Oper Mgmt, Sustainable Operations Sponsored Session Chair: Michael Lim, U of Illinois at Urbana-Champaign, Champaign, IL, United States, mlim@illinois.edu Co-Chair: Karthik Murali, University of Alabama, Tuscaloosa, Tuscaloosa, AL, United States, kmurali@cba.ua.edu 1 - Optimal Feed-in Tariff Policies: The Role Of Technology Manufacturers Shadi Goodarzi, HEC, Paris, France, shadi.goodarzi@hec.edu Sam Aflaki, Andrea Masini We assess the effectiveness of feed-in tariff policies in promoting renewable energy technologies taking into account technology manufacturers’ decisions. Modeling a three-tier supply chain that includes potential adopters, technology manufacturers and a grid operator, we show that the ability of feed-in tariffs to induce renewable energy adoption is strongly affected by the technology manufacturers’ market characteristics. 2 - Product Allocation Under The Risk Of Recall Long He, National University of Singapore, longhe@nus.edu.sg, Ying Rong, Zuo-Jun Max Shen When product recalls happen, companies not only have to deal with additional logistics costs but also a damaged reputation. To alleviate the severe consequences of product recall, we develop a model to compare dedicated and uniform product allocation strategies with associated sourcing plans. We also discuss the impacts of key factors in the performance comparison.

Empirical Research in Healthcare Operations Sponsored: Manufacturing & Service Oper Mgmt, Service Operations Sponsored Session Chair: Mor Armony, New York University, Stern School of Business, New York, NY, 10012, United States, marmony@stern.nyu.edu 1 - Refining Workload Measure In Hospital Units: From Census To Acuity-adjusted Census In Intensive Care Units Song-Hee Kim, Marshall School of Business, University of We aim to better understand the impact of ICU workload on patient outcomes, so that practitioners and researchers can use such understanding to provide high quality care despite increased hospital crowding. Using data from two ICUs and a dynamic measure of patient acuity, we show when acuity-adjusted workload is high sicker patients are discharged and longer-term outcomes are affected. Our findings suggest 1) ICUs need to track changes in patient acuity and 2) future studies of ICU workload should take patient acuity into account in workload measures. Using a simulation study, we show how high acuity-adjusted workload can be prevented by reducing seasonality in patient arrivals. 2 - Data-driven Appointment Scheduling Under Uncertainty: The Case Of An Infusion Unit In An Oncology Center Nikolaos Trichakis, MIT, Cambridge, MA, United States, ntrichakis@mit.edu, Avishai Mandelbaum, Petar Momcilovic We develop a novel, data-driven approach to deal with appointment sequencing and scheduling in a multi-server system, where both customer punctuality and service times are stochastic. Our approach relies on an infinite-server queuing model approximation. We calibrate our model using a data set of unprecedented resolution, gathered at a large-scale outpatient oncology practice, and illustrate how our approach can be utilized to improve infusion scheduling. We also demonstrate the performance of our approach by comparing it with existing state- of-the-art sequencing and scheduling algorithms. 3 - The Effect Of Online Reviews On Physician Demand: A Structural Model Of Patient Choice Yuqian Xu, NYU, yxu@stern.nyu.edu, Mor Armony, Anindya Ghose Social media platforms for healthcare services are changing how patients choose doctors. In this paper, we wish to derive the impact of online information on patient choice of outpatient care doctors. We are especially interested in how operational factors influence demand. We propose a random coefficient logit model to characterize consumer heterogeneity in doctor choices, taking into account both numeric and textual user-generated content with text mining techniques. Our interdisciplinary approach provides a framework that combines machine learning and structural modeling techniques with empirical operations management. Southern California, Los Angeles, CA, United States, songheek@marshall.usc.edu, Edieal Pinker, Joan Rimar, Elizabeth Bradley Empirical and Theoretical Models in Supply Chains Sponsored: Manufacturing & Service Oper Mgmt, Supply Chain Sponsored Session Chair: Anyan Qi, The University of Texas at Dallas, Business School, Richardson, TX, 11111, United States, axq140430@utdallas.edu Co-Chair: Ozge Sahin, Johns Hopkins University, 100 International Drive, Baltimore, MD, 21202, United States, ozge.sahin@jhu.edu 1 - Assessing Uncertainty From Point Forecasts Zhi Chen, INSEAD, Singapore, Singapore, Zhi.Chen@insead.edu, Anil Gaba, Dana Popescu This paper develops a parsimonious model for combining correlated point forecasts into a probability distribution for the quantity of interest. The model is compared with other commonly used methods that either ignore the lack of dependence between the point forecasts and/or use a certainty equivalent approach in estimating the distribution parameters, hence ignoring the parameter uncertainty. We further illustrate the implications for a decision maker in a newsvendor setting, where our model leads to profits that are higher on average when compared to the other widely used methods. MB36 205B-MCC

160