Informs Annual Meeting 2017

MD39

INFORMS Houston – 2017

MD38

2 - A Data-Driven Approach to Personalized Bundle Pricing and Recommendation Anna M. Papush, Massachusetts Institute of Technology-ORC, Somerville, MA, 02143, United States, apapush@mit.edu, Georgia Perakis, Pavithra Harsha The growing trend in online shopping has sparked the development of increasingly more sophisticated product recommendation systems. We construct a model that recommends a personalized discounted product bundle to a shopper that considers the trade-off between profit maximization and inventory management, while selecting relevant products to the consumer’s preferences. We develop two classes of approximation algorithms to produce output in real-time. We provide analytical performance guarantees and implement our algorithms on data from a large U.S. e-tailer and a premier global airline. Our results show significant lifts in expected revenue over current practices on the order of 2-7%. 3 - Coopetition and Profit Sharing for Ride-sharing Platforms Renyu Zhang, New York University Shanghai, Shanghai, China, renyu.zhang@nyu.edu, Maxine Cohen The recent introduction of on-demand ride-hailing and ride-sharing platforms totally changed the way people commute. We consider a setting in which two competing platforms engage in a profit sharing contract by introducing a new hybrid service. We model the price competition between the platforms by using the Multinomial Logit model, and show that a unique equilibrium exists. Then, we analyze the impact of introducing the new joint service to the market. Interestingly, we show that a well-designed profit sharing contract benefits every single party (riders, drivers and both platforms). Chair: Eleftherios T. Lakovou, Texas A&M Engineering Experiment Station, Texas A&M Engineering Experiment Station, College Station, TX, 77840, United States, eiakovou@tamu.edu 1 - Evaluating a Wicked Problem: A Conceptual Framework on Seaport Resiliency Amir Gharehgozli, Texas A.& M.University, P.O. Box 1675, Galveston, TX, 77553, United States, gharehga@tamug.edu Seaport infrastructure by virtue of its location can be severely impacted from disruptive adverse weather events. Disruptive adverse events range from long- term changes such as sea level rise caused by climate change to short-term impacts such as hurricanes. This paper proposes a new conceptual framework for evaluating how ports currently strategize against the risks associated with these potential events and how they plan to ensure port resiliency. 2 - Information Dashboards for Enabling Business Continuity and Risk Management Jim Wall, Texas A&M.University, TEES.Headquarters, 3470 TAMU, College Station, TX, 77843-3577, United States, jim-wall@tamu.edu, Keith Biggers Decision makers routinely need quick access to dependable and relevant data to adequately assess risk to inform necessary decision making processes. We provide an overview of ongoing research and development of a technology platform for enhancing situational awareness and decision support including the implications for training. This platform allows for visual integration of disparate real-world data streams into a common user-defined operational picture. Data sources can include databases, sensors, and results from simulations. We will illustrate how this platform can support business continuity, logistics, and risk and consequence management across a range of real-world applications. 3 - A Game Theory-based Strategic Framework for Border Security Control and Risk Management for Protecting Globalized Supply Chains Against Illicit Use Yanling Chang, Texas A&M.University, 1550 Crescent Pointe Pkwy, Adversaries often utilize global supply chains as targeted delivery platforms by transporting illegal or unauthorized goods into the U.S. Such breaches may result in negative economic ramifications for all supply chain stakeholders or for launching a terrorist attack. This research aims to develop a novel, dynamic, quantitative strategic framework based on game theory to capture and understand the supply chain risk imposed by such adversaries for ensuring border security along with business continuity and supply chain resilience, while further securing the four flows of supply chains - products, process/work, information, and cash across the border. MD37 352B Border Security, Risk Management and Resilience for Global Supply Chains Sponsored: Service Science Sponsored Session APT.1206, College Station, TX, 77845, United States, yanling.chang@tamu.edu, Eleftherios Iakovou, Jim Wall, Keith Biggers

352C Analytic Network Process (ANP) Best Practices Sponsored: Multiple Criteria Decision Making Sponsored Session Chair: Orrin Cooper, University of Memphis, Memphis, TN, 38152, United States, olcooper@memphis.edu 1 - Implications of Coherency: A Literature Review Orrin Cooper, University of Memphis, 332 Ba, Memphis, TN, 38152, United States, olcooper@memphis.edu, Enrique Mu, Michael Peasley Coherency is an important test to run when creating ANP models. This claim is further motivated by reviewing all ANP publications from 2015 in the SSCI Index. Summary data of the publications’ coherency levels and impacts on the final results when attempts were made to improve coherency are presented. These results provide additional motivation for Coherency testing. Simulations results are presented to generalize the effect incoherency can have on the results of an ANP model. 2 - After 25 Years ANP Best Practices Enrique Mu, Carlow University, 3333 Fifth Avenue, Pittsburgh, PA, 15213, United States, emu@carlow.edu The rule of thumb for scientific reports has been to provide enough information so the study can be understood, assessed its methodological validity and -given access to the proper dataset- to allow its replication. We have reviewed SSCI- indexed ANP studies published during 2015 and found that most of them are inconsistent in terms of what they report. While there are currently no specific rules about how to report ANP studies, we propose here some guidelines -to our knowledge, for the first time- to properly report them. 3 - Does a Shared-decision Making Model for Colorectal Cancer Screening Lead to Better Medical Outcome? M. Gabriela Sava, College of Business, Clemson University, Clemson, SC, United States, msava@clemson.edu, Luis G. Vargas, Jerrold H. May, James G. Dolan Choosing the most appropriate colorectal cancer screening option should be a joint decision, made by both the patient and the healthcare provider. We propose a multi-criteria decision making model that combines the patient’s preferences regarding the currently available cancer screening options with the healthcare provider’s expertise. The most preferred option is further analyzed, to assess its sensitivity and stability as additional medical information might be brought into the discussion. Chair: Xueping Li, University of Tennessee, 1350 Pershing Hill Lane, Knoxville, TN, 37919-0700, United States, xueping.li@gmail.com 1 - Understanding Treatment Strategies of Sepsis using a Decision Framework Zhenzhen Shi, Post Doctoral Fellow, Kansas State University, P200 Mosier Hall, Manhattan, KS, 66506, United States, szztracy@ksu.edu, David Ben-Arieh, John C.Wu, Majid Jaberi-Douraki Strategies for sepsis treatment have been discussed extensively in recent years, but no general agreement exists regarding efficacy of these strategies. This lack of consensus is due to the complex nature of what causes sepsis to progress, including heterogeneous groups of patients with infections caused by various microorganisms. Based on our computational-based decision framework, we found out the efficacy of treatment strategies is dependent on various parameters including the type of treatment, the time of treatment administration, the amount of treatment implementation, and the various groups of individuals. 2 - Doctors Performance in Emergency Room Amir Mousavi, George Washington University, 475 K.St NW, Apt 419, Washington, DC, 20001, United States, ahmn00@gmail.com, Hernand Abeledo, Imad Khojah Emergency Rooms are known as a fast paced and extremely vital ward in a hospital. Improving the efficiency in the ER has been a challenging question for researchers. Throughout the academic literature, people have defined different efficiency indexes and different decision variables in order to tackle this problem. This research aims to apply DEA techniques in order to identify the performance (i.e. productivity) variation among doctors and use this result as a component of the optimization model in order to improve the efficiency of the system. MD39 352D Practice/Healthcare I Contributed Session

249