2016 INFORMS Annual Meeting Program

TD08

INFORMS Nashville – 2016

TD09 103B-MCC Big Data II Contributed Session

3 - Parallel Computing For The Optimization Of A Large-scale Dynamic Network - The Internet Of Hearts Chen Kan, Pennsylvania State University, University Park, PA, 16802, United States, cjk5654@psu.edu, Hui Yang Rapid advancements of mobile computing provide an unprecedented opportunity to empower a next generation mobile health system - the internet of heart (IoH). The IoH embeds patients into a dynamic network and reveals the change of patient’s status through network variations. However, it poses a great challenge for real-time recognition of disease patterns when large number of patients are involved in IoH. This study develops a novel scheme to optimize the network in a parallel, distributed manner, thereby improving the the efficiency of computation. Experimental results show that the developed scheme is effective and efficient for realizing smart connected healthcare in large-scale IoH contexts. 4 - Control Policies For Iot Manufacturing Systems: A Two Stage Stochastic Approach Xu Jin, Texas A&M University, College Station, TX, United States, jinxu@tamu.edu, Natarajan Gautam, Satish Bukkapatnam, Hoang Tran We consider a smart manufacturing setting where materials and machines are part of an IoT. A two-stage stochastic model is formulated to determine tool replacement and processing speed decisions based on the availability of the job arrival as well as machine health and processing status information. Stage 1 uses a Lyapunov method to cluster jobs for throughput optimization, and Stage 2 employs a stochastic scheduling algorithm to minimize cycle times. We also analyze the effectiveness of this approach using extensive numerical testing. TD08 103A-MCC Outsourcing Innovation Invited: Business Model Innovation Invited Session Chair: Ersin Korpeoglu, University College London, London, United Kingdom, e.korpeoglu@ucl.ac.uk 1 - Performance Feedback In Competitive Product Development Daniel P Gross, Harvard Business School, dgross@hbs.edu Performance feedback is ubiquitous in competitive settings where new products are developed. This paper introduces a tension between incentives and improvement in performance evaluation. Using a sample of four thousand commercial logo design tournaments, I show that feedback reduces participation but improves the quality of submissions, with an ambiguous effect on high- quality output. To evaluate this tradeoff, I develop a procedure to estimate agents’ effort costs and simulate counterfactuals under alternative feedback policies. The results suggest that feedback on net increases the number of high-quality ideas produced and may thus be desirable for a principal seeking innovation. 2 - Workforce Mobility And Innovation Outcomes In Manufacturing Philipp Cornelius, University College London, London, United Kingdom, philipp.cornelius.12@ucl.ac.uk, Bilal Gokpinar, Fabian Sting Employee ideas are a valuable starting point to improve operational efficiency. We empirically investigate how moves between problems and sites affect the innovation value created by employee ideas for the organization. We document that the dynamic effects of problem switches differ fundamentally from the effects of site switches: The innovation outcomes of problem switching employees follow a concave inverse u-shaped pattern, whereas the innovation outcomes of site switching employees follow a convex u-shaped pattern over time. We discuss implications for theory. 3 - Contest Among Contest Organizers Ersin Korpeoglu, School of Management, University College London, London, United Kingdom, e.korpeoglu@ucl.ac.uk, Isa E Hafalir This paper analyzes the organization of multiple innovation contests in which organizers post problems to a group of agents, and elicit innovative solutions. We compare the contest organizers’ payoffs when they organize multiple contests simultaneously or when they compete with other contest organizers for the effort of agents towards solving their problems. We show that depending on problem structure, more intense competition among organizers and organizing multiple contests may harm or, counter-intuitively, benefit each organizer. Our findings explain why organizers find it beneficial to hold multiple contests or organize similar contests with their competitors simultaneously.

Chair: Haibo Wang, Killam Distinguished Associate Professor, Texas A&M International University, 5201 University Boulevard, Laredo, TX, 78045, United States, hwang@tamiu.edu 1 - Integrating Data Science In Statistical Practice And Analytics

Steven B Cohen, RTI International, 701 13th Street NW, Washington, DC, 20005, United States, scohen@rti.org

The field of data science has served to rapidly expand the knowledge base and decision-making ability through the combination of seemly disparate and diverse sources of information and content, which include survey and administrative data, social, financial and economic micro-data, and content from mobile devices, the internet and social media. Other attributes of data science include data visualization; predictive, mathematical and simulation modeling; use of Bayesian methods, machine learning; GIS and geospatial analytics and Big Data technologies. In this presentation, attention is given to demonstrate the capacity Michael Chuang, State University of New York, 1 Hawk Drive, New Paltz, NY, 12561, United States, chuangm@newpaltz.edu NGS analysis presents a domain for biomedical and information technology professionals to explore. Due to the large amount of data involved and various constraints of technologies, we delineate issues to consider to develop a framework using parallel computing and NoSQL database service to greatly reduce the required time under less infrastructure investments while achieving satisfactory accuracy. 3 - Five Steps To Big Data Analytics Xuan Wang, PhD Student, Louisiana State University, 2200 Business Education Complex, Nicholson Extension, Baton Rouge, LA, 70803, United States, xwang35@lsu.edu, Helmut Schneider Analytics has been categorized as descriptive, predictive and prescriptive. However, much many challenges lie in the data preparation. Also, analytics is typically concerned about prediction rather than explaining, leaving manager’s to question whether to trust results. Hence, data preparation and causal inference are two important steps in analytics at the beginning and end of an analytics project life cycle. 4 - Prescriptive Analytic For Public Transportation Corridor Planning Haibo Wang, Killam Distinguished Associate Professor, Texas A&M International University, 5201 University Boulevard, Laredo, TX, 78045, United States, hwang@tamiu.edu, Wei Wang, Jun Huang We investigate how public transportation planning affects the economic growth and social development in the urban areas, especially the economic enhancement zones in US cities. We build visualization tools to help decision makers understand the impact of future planning and issues of existing system. TD10 103C-MCC Optimization in Renewable Energy Sponsored: Energy, Natural Res & the Environment, Energy II Other Sponsored Session Chair: Sushil Raj Poudel, MSU, MSU, Starkville, MS, 39760, United States, srp224@msstate.edu 1 - Sustainable Network Design For Multi-purpose Pallet Processing Depots Under Biomass Supply Uncertainty MD Abdul Quddus, PhD Student, Mississippi State University, Department of Industrial & Systems Engineering, P.O. Box 9542, Starkville, MS, 39762, United States, mq90@msstate.edu, Niamat Ullah Ibne Hossain, Mohammad Marufuzzaman, Raed Jaradat This study develops a two-stage stochastic mixed-integer programming model to manage sustainable pellet processing depots under feedstock supply uncertainty. The proposed optimization model not only minimizes cost but also mitigates emissions from the supply chain network. We develop a hybrid decomposition algorithm that combine Sample average approximation with an enhanced Progressive Hedging (PH) algorithm. Mississippi and Alabama are selected for testing ground of this model. The results of the analysis reveal promising insights that could lead to recommendations to help decision makers to achieve a more cost-effective environmentally-friendly supply chain network. of data science to enhance study designs and predictive analytics. 2 - Next-generation Sequencing (NGS) Data Analysis: Developing A Scalable Framework For The Future

336