Informs Annual Meeting 2017

SA20

INFORMS Houston – 2017

SA18

chain: if tier 1 suppliers share tier 2 suppliers, resulting in a “diamond-shaped” supply chain, the buyer relies less on direct mitigation (procuring excess inventory and multisourcing in tier 1) and more on indirect mitigation (inducing tier 1 suppliers to mitigate disruption risk). 2 - Risky Suppliers or Risky Supply Chains Yixin Wang, University of Michigan, 701 Tappan Street R4323, Ross School of Business, Ann Arbor, MI, 48104, United States, iriswang@umich.edu, Jun Li, Ravi Anupindi Past research has focused on the interaction between a buyer and its immediate suppliers. Propagation of risks, however, can extend beyond a firm’s direct linkages. The sub-tier supply network structure may also aid or prevent such risk propagation. This paper focuses on a particular sub-tier network structure, viz., sharing of tier-2 suppliers, empirically studies its prevalence, and quantifies its association with the financial risk of tier-0 firms in the high-tech industry. 3 - Mitigating Disruption Cascades in Assembly Networks Shyam Mohan, London Business School, Baker Street, PhD Office, London, NW1 4SA, United Kingdom, smohan@london.edu, Nitin Bakshi The losses from supply chain disruptions arise not only due to direct damage at firms (from idiosyncratic disruptions), but also from the interruption of normal operations because of lack of supply; that is, due to disruption cascades from suppliers in the adjacent tiers and beyond. To curtail such losses, firms can make ex-ante investments in mitigation and recovery strategies. In this paper, we examine a game-theoretic framework to characterize equilibrium investments and payoffs of firms in an assembly network. We show that limited information about the network structure suffices for firms to make optimal investments. 4 - Learning (or not) from Precursors to Disasters Heikki Peura, Imperial College London, London, United Kingdom, h.peura@imperial.ac.uk, Nitin Bakshi Disasters are invariably preceded by more frequent precursor events. These events embed valuable information about the root cause of a disaster, and thereby facilitate risk assessment. But to learn from precursors, a managing firm typically relies on the reports of a contractor, who is often also responsible for mitigating the occurrence of these incidents. We show how firms may fail to learn from precursor events due to the resulting intertwined problems of moral hazard (on risk mitigation) and hidden information (on reporting precursors).

340B Stochastic Networks and Queueing in Applied Probability I Sponsored: Applied Probability Sponsored Session Chair: Harsha Honnappa, Purdue University, West Lafayette, IN, 47906, United States, honnappa@gmail.com 1 - Analysis of Abandonments in Ticket Queues: A Bayesian Approach Kaan Kuzu, University of Wisconsin-Milwaukee, Sheldon B. Lubar School of Business, P.O. Box 742, Milwaukee, WI, 53201-0742, United States, kuzu@uwm.edu, Refik Soyer Ticket queues collect interval censored data for customer abandonment. The abandonment of a customer is only realized when the ticket for that customer is called for service and the customer does not show up. Using a modulated Poisson process model as the framework, we develop parametric and semi-parametric models and their Bayesian analysis to predict abandonment counts on any interval. We also explore the impact of covariates such as queue position, number of servers, and day of the week on predicted abandonment counts. The proposed models are implemented on a real ticket queue data set to provide managerial insights on server allocation. 2 - Delay Announcements with Customer Response Rouba Ibrahim, University College London, MS&I Department, UCL, Gower Street, London, WC1E 6BT, United Kingdom, rouba.ibrahim@ucl.ac.uk, Mor Armony, Achal Bassamboo We study the accuracy of the last-to-enter-service (LES) delay announcement in service systems where customers respond to the announcements. 3 - Optimal Production Rates for Large Scale Systems under Time-varying Demand Chihoon Lee, Stevens Institute of Technology, Hoboken, NJ, 07030, United States, clee4@stevens.edu, Yunan Liu, Xin Liu, Ling Zhang Continuous manufacturing has received much of recent attention both in academia and industry. We consider production systems with a time-varying demand, perishable inventory, and abandonment of backorders. The system incurs inventory-related costs of holding and perishment, and demand-related costs of waiting and abandonment. We study the finite-time production planning to minimize the sum of the demand and production related costs. We use fluid models to derive time-dependent production rates that are asymptotically optimal as the system scale increases; specifically, we prove a limit theorem to verify the asymptotic effectiveness of the optimal solution. 4 - Club Queues Jamol Pender, Cornell University, 206 Rhodes Hall, Ithaca, NY, 14850, United States, jjp274@cornell.edu, Andrew Daw In many stochastic systems, the arrival process may exhibit clustering behavior. This behavior is typically seen in financial markets and is also seen at nightclubs in New York City and Las Vegas. Using martingales, we derive exact moments and moment generating function for an infinite server queue that is driven by a Hawkes process and has phase type service. We show via simulation that the moments well approximate the simulated moments. As an application, we apply our results to study a queueing process described as the Club queue. As a result, we derive the optimal rate at which a bouncer should allow clubgoers to go inside the club using optimal control theory with the mean of our Hawkes queueing process. 342A Disruption Risk Management Sponsored: Manufacturing & Service Oper Mgmt, iFORM Sponsored Session Chair: Nitin Bakshi, University of Utah, Salt Lake City, UT, 84112-8939, United States, nitin.bakshi@eccles.utah.edu 1 - Disruption Risk and Optimal Sourcing in Multitier Supply Networks Dan Andrei Iancu, Stanford University, 655 Knight Way, Stanford, CA, 94107, United States, daniancu@stanford.edu, Robert Swinney We study sourcing in a supply chain with three levels: a buyer, tier 1 suppliers, and tier 2 suppliers prone to disruption from, e.g., natural disasters. The buyer may not directly dictate which tier 2 suppliers are used but may influence the sourcing decisions of tier 1 suppliers via contract parameters. We show that the buyer’s optimal strategy depends critically on the degree of overlap in the supply SA19

SA20

342B Management of Innovation, Technology and Services Sponsored: Technology, Innovation Management

& Entrepreneurship Sponsored Session

Chair: Juliana Hsuan, Copenhagen Business School, jh.om@cbs.dk 1 - The Impact on the Pricing of Hotel Rooms using New Technology Eric Bentzen, Copenhagen Business School, Frederiksberg, Denmark, eb.om@cbs.dk In this paper we will investigate the dynamic pricing of hotel rooms among customers who use online booking apps. Online booking apps allow you to start making reservations directly using apps on smartphones, ipads, and PCs. The empirical results based on data from 2016-2017 show that the pricing structure depends on the type of customer, time of the year, number of hotels and the number of days in advance a hotel is booked. 2 - Nescience: A Key Ingredient to Managing Innovation Nitin Mayande, Nike, 6249 NE Carillion Drive, Unit 201, Hillsboro, OR, 97124-8097, United States, nitin.mayande@nike.com, Charles M. Weber, Rainer P. Hasenauer Aristotle’s dictum scio nescio (I know that I don’t know) may serve as a source of enhanced performance for organizations. Awareness of nescience sets the direction for further inquiry, as managers tend to move in the direction that they believe will reduce nescience most. However, nescience is difficult to quantify, so, to date, managers have primarily relied on intuition. Observing business analytics practices in three industries—semiconductor manufacturing, medical diagnostics and social media analytics—suggests that nescience can be measured using metrics from information theory.

9