Informs Annual Meeting 2017

TE16

INFORMS Houston – 2017

3 - Predicting Patient Treatment Deferrals/no-shows to Improve Chemotherapy Pre-Mix Policies Donald B. Richardson, University of Michigan, 2753 IOE Building, 1205 Beal, Ann Arbor, MI, 48109-2117, United States, donalric@umich.edu, Amy Cohn In collaboration with the University of Michigan Comprehensive Cancer Center, we have developed a predictive model to determine the probability that a patient will not show for or defer treatment on a given day. This information can then be used in our proposed expected drug waste cost functions to aid outpatient chemotherapy centers in deciding which drug to make-ahead. We test a wide range of predictive models including Generalized Linear models (GLM), tree- based methods, Neural Networks, and various Ensemble models. This work complements our optimization model which determines the superior set of drugs to make ahead to reduce patient waiting time in the outpatient cancer center. 4 - Sequencing Patients for Ancillary Service in an Inpatient Unit Pratik Parikh, Associate Professor, Wright State University, Dayton, OH, 45435, United States, pratik.parikh@wright.edu, Nicholas Ballester, Nan Kong, Jordan Peck Ancillary service providers on an inpatient unit, such as social workers, care managers, and physical and occupational therapists, play crucial roles in the inpatient discharge process. However, these providers are also responsible for other patients besides those to be discharged. There is a paucity of research suggesting an optimal patient sequencing strategy for these providers. We model this problem similar to a stochastic single machine sequencing problem with side constraints. Using a simulation-optimization approach, we derive near-optimal policies and benchmark industry practice. 332E Sustainable Supply Chains Sponsored: Manufacturing & Service Oper Mgmt, Supply Chain Sponsored Session Chair: Basak Kalkanci, Georgia Institute of Technology, Atlanta, GA, 30339, United States, basak.kalkanci@scheller.gatech.edu 1 - Voluntary vs. Compulsory Supplier Sustainability Assessments in Supplier Selection Karca Duru Aral, Assistant Professor, Syracuse University, 721 University Avenue, Syracuse, NY, 13244, United States, kdaralwa@syr.edu In order to make an informed supplier selection during a total-cost procurement auction, the buyer can choose to make sustainability assessments compulsory for the competing suppliers. However, this would negatively affect competition as some suppliers can drop out of the auction given the assessment costs. The buyer can instead make assessments voluntary - but would then risk making a less informed selection. We analyze this trade-off and identify how the buyer should set her assessment policy. 2 - Worker Flexibility Training and Production Autonomy Evan Barlow, Weber State University, Goddard School of Business & Economics, 1337 Edvalson St, Ogden, UT, 84408, United States, evanbarlow@weber.edu, Gad Allon, Achal Bassamboo We explore the interaction between worker production autonomy and workers’ decisions on training to become flexible resources. Research on flexible resources is prevalent in the operations management literature. Human resources, however, are decision makers and have rights to decide on their own training levels. Many firms, however, have also given workers some production autonomy. We show how workers’ training decisions are affected by the identity of the production decision maker. 3 - When to Source from a Competitor? Eda Kemahlioglu Ziya, North Carolina State, Poole College of Management, Campus Box 7229, Raleigh, NC, 27695-7229, United States, ekemahl@ncsu.edu, Olga Perdikaki We study the outsourcing decisions of an original equipment manufacturer (OEM). One option is to source from an independent supplier and the other is to source from an integrated firm who is also a competitor of the OEM in the consumer market. However, the advantage of the latter option is that the independent supplier can achieve lower production cost by exploiting the manufacturing synergies between the two products. We also study how/if the OEM’s decision is impacted by the type of contract between the OEM and it’s supplier. TE15

4 - Selling Off-grid Light to Liquidity Constrained Consumers Bhavani Shanker Uppari, INSEAD, 1 Ayer Rajah Avenue, Singapore, 138676, Singapore, BhavaniShanker.UPPARI@insead.edu, Ioana Popescu, Serguei Netessine A large proportion of the world’s population has no access to electricity and so relies on noxious kerosene for their lighting needs. As an alternative, there are business models relying on rechargeable light bulbs that are sold at a subsidized price (which renders them affordable) and require regular micropayments for recharges (which eases liquidity constraints). These bulbs provide a cheaper and healthier light source than kerosene, yet their adoption is lower than expected and some consumers continue to use kerosene. This paper explores the potential drivers of such preferences and proposes strategies to alter them. 332F Operations Management Contributed Session Chair: Xiaojing Feng, Shanghai Jiao Tong University, Shanghai, China, fengxj89@sjtu.edu.cn 1 - How Market Power Impacts Invest in Supply Chain Jingjie Su, University of Texas at Arlington, 2508 Mustang Drive, Arlington, TX, 76001, United States, jingjie.su@mavs.uta.edu Consider a supply chain network with two players, one is original equipment manufacturers and another is contract manufactures.. OEM and CM have relationships both as downstream supplier and competitor in the market. In this supply chain network, when OEM is deciding about making an investment to lower the cost of the product, based on different investment cost and market power, the Nash Equilibrium theory predicts the different decision. We conduct a series of experiments, varying the investment cost and market power, and find out that the experiment data varies from theory. We then apply behavior models to explain these difference. 2 - Prescriptive Analytics for Optimizing the Scheduling of Maintenance Operations Stefan Feuerriegel, University of Freiburg, Maintenance of industrial components frequently occurs upon failure, thereby incurring costs from down-times. A remedy is given by preventive maintenance, for which we propose a prescriptive methodology that schedules maintenance events in order to minimize the service-related costs. This approach consists of two stages: first, we predict the time-to-service of machines based on sensor data using machine learning. In the second stage, we identify the optimal timing of maintenance operations. Here the key ingredient of this work is the fusion of prediction and optimization. We demonstrate the effectiveness of our approach in a case study with real-world data from a large wind park operator. 3 - An Investigation of the Impacts of Nurse Slack on Care Quality and Operating Costs Xiaosong (David) Peng, Associate Professor, University of Houston, 511 Somerset Dr, Sugarland, TX, 77479, United States, xpeng@bauer.uh.edu, Yuan Ye, Xin Ding As value-based purchasing (VBP) and patient-centered care take the center stage in today’s healthcare environment, healthcare organizations including hospitals are in an ongoing quest to improve both clinical quality and (patient) experience quality while containing rapidly rising costs. To improve and control clinical quality and experiential quality, hospitals must carefully determine the level of nurse slack, defined as the amount of nurse capacity relative to the amount of work performed. This research seeks to identify the fine-grained relationships between nurse slack and clinical quality, experiential quality, and operating costs. 4 - In-house vs Outsourcing: the Effect of Volume-based Learning on Quality Competition Yanni Ping, PhD Candidate, Drexel University, 3220 Market Street, Philadelphia, PA, 19104, United States, yp86@drexel.edu, Seung-Lae Kim This paper considers an original equipment manufacturer (OEM) who outsources finished products from an contract manufacturer (CM) where the CM, by adopting existing technology, achieves cost reduction and quality improvement through learning-by-doing. Besides the role of upstream partner, the CM also acts like a downstream competitor. We study the OEM’s outsourcing strategy dynamically when competition exists and does not exist. We construct a two- period model and explore the interplay of learning, quality and cost and identify the condition under which pure outsourcing, partial outsourcing or non- outsourcing outplays the others. Platz der alten Synagoge, Freiburg, 79098, Germany, stefan.feuerriegel@is.uni-freiburg.de, Niklas Goby, Dirk G. Neumann TE16

415