Informs Annual Meeting Phoenix 2018

INFORMS Phoenix – 2018

SB15

3 - Managing the Callback Option under Arrival Rate Uncertainty Xiaoshan Peng, Indiana University, Kelley School, Bloomington, IN, United States, Baris Ata We study how to manage the callback option eectively to mitigate congestion due to temporary surges in the arrivals to a call center. Initially, we allow complete foresight policies that look into the entire future. We consider the setting where some customers may reject the callback offer. We show that a modified lookahead policy that looks into the future arrivals and service completion times for the next p/h time units and uses the current number of customers in the system who previously rejected a callback offer is pathwise optimal. Building on the insights gleaned from the optimal lookahead policies, we also propose a non-anticipating policy, referred to as the line policy. 4 - Using Hospital Admission Predictions at Triage for Improving Patient Flow Serhan Ziya, University of North Carolina, Department of Stat and OR, 356 Hanes Hall Cb#3260, Chapel Hill, NC, 27599, United States, Sukriye Nilay Argon, Wanyi Chen We investigate how predictions for hospital admissions at the time of triage can be used to reduce boarding times and overall emergency department length-of-stay. Using simple mathematical models, we develop methods for making early bed reservations for patients at triage depending on the predictions for hospital admissions and also possibly on time-of-day and census levels. We then compare the performances of these methods using a simulation model constructed using data from an emergency department. n SB15 North Bldg 127A Innovative Business Models Sponsored: Manufacturing & Service Oper Mgmt/Service Operations Sponsored Session Chair: Kamalini Ramdas, London Business School, London, NW1 4SA, United Kingdom 1 - Mobile Technology in Online Retail: Strengths and Limitations Jose A. Guajardo, University of California-Berkeley, Haas School of Business, 545 Student Services Bldg, Berkeley, CA, 94720-1900, United States We empirically analyze central aspects of the role of mobile technology in the overall customer experience in online retailing. 2 - Impact of After Sales Service on Technology Adoption in Emerging Markets Amrita Kundu, London Business School, Regent’s Park, PhD Office - MSO, London, NW1 4SA, United Kingdom, Kamalini Ramdas We aim to empirically assess the impact of after-sales interactions on adoption and continued use of new technology in emerging markets. In particular, we estimate the impact of after-sales service and customer engagement on new customer acquisition and customer retention for a solar distribution company operating in off-grid communities in East Africa. We combine a proprietary dataset obtained from a solar distribution company and secondary data sources to estimate the market impact of after-sales interactions. 3 - When is the Root of All Evil Not Money? The Impact of Load on Operational Risk at a Commercial Bank Yuqian Xu, University of Illinois at Urbana-Champaign, Wohlers Hall 487, 1206 S. 6th St, Champaign, IL, 61820, United States, Fangyun Tan, Serguei Netessine We use a unique operational risk event data set from a commercial bank in China that contains 1,441 operational risk events in two years. We find that workload has a U-shaped impact on operational risk frequency. In addition, we show that workload has an inverted-U shaped impact on bank profit. We compare our optimal staffing policy with bank’s original policy, and estimate that the new staffing policy would reduce the current number of employees by 7.56%, which would further decrease the number of risk events by 4.51%, cut the total losses by 4.58%, and increase profits by 1.24%.

n SB16 North Bldg 127B Sustainable Operations Sponsored: Manufacturing & Service Oper Mgmt/Sustainable Operations Sponsored Session Chair: Basak Kalkanci, Georgia Institute of Technology, Atlanta, GA, 30339, United States 1 - Encouraging Energy Efficiency Investment in a Supply Chain: A Behavioral Investigation Jason Quang Nguyen, University of New South Wales, UNSW Business School, Sydney, 2052, Australia, Karen L. Donohue, Behrooz Pourghannad Suppliers’ propensity to accept external assistance from third-party organizations and buyers and undertake subsequent Energy Efficiency investments is still elusive. Through controlled behavioral experiments, this paper studies how the source of external assistance, contract framing and characteristics of the investment influence the supplier’s propensity to undertake the assessments and subsequent investments. 2 - Predicting Carbon Abatement Disclosures using Text Analysis Christian Blanco, Ohio State University, 640 Fisher Hall, 2100 Neil Ave Columbus, Columbus, OH, 43201, United States Firms may choose not to disclose financial information on carbon abatement opportunities for various reasons. One reason for this is that firms are strategic about what they may disclose. Another reason is that firms may not yet be aware of the precise outcome of these opportunities. We explore conditions when firms may or may not disclose financial information on carbon abatement opportunities. We will explore this question using over 40,000 carbon abatement opportunities reported to CDP from 2011-2016. 3 - The Impact of Input- vs. Output-based Farm Subsidies on Farmer Welfare and Income Inequality Yulan Wang, Hong Kong Polytechnic University, Department of Logistics and Maritime Studies, Faculty of Business, Kowloon, Hong Kong, Christopher S. Tang, Ming Zhao We examine the implications of two commonly observed farm subsidy schemes in this paper. The first scheme is input-based while the second is output-based. By analyzing a stylized model that captures the yield heterogeneity across farmers who engage in quantity competition, we find that both schemes can improve farmers’ income. However, the input-based subsidy scheme narrows the income gap between farmers, but the output-based scheme widens this gap. The output- based subsidy scheme outperforms the input-based subsidy scheme in terms of total farmer income and farmer productivity. We find these results continued to hold when the farmer’s yield rate is uncertain. 4 - How Does Regulation Stimulate the Good and the Bad Innovations? Keija Hu, Owen School of Business, Vanderbilt University, Nashville, TN, United States, Mark Cohen Using data to quantify the technology progress in the auto industry in the past 20 years, we analyze how regulation simulates both the good and bad innovations. n SB17 North Bldg 127C Data-Driven Supply Chain Operations Sponsored: Manufacturing & Service Oper Mgmt/Supply Chain Sponsored Session Chair: Max Shen, JD.com, Santa Clara, CA, 95054, United States Co-Chair: Sheng Liu, University of California, Berkeley, Berkeley, CA, 94709, United States 1 - Bayesian Inventory Management: Demand Learning via Exploration Boosts Michael Kim, PhD, Sauder School of Business, University of British Columbia, Vancouver, BC, Canada We investigate inventory management problems where parameters of the demand distribution are not known a priori, but need to be learned using right- censored sales data. The goal of this paper is to characterize the structure of the optimal inventory policy to better understand the basic mechanism by which learning and inventory control are optimally combined. To this end, through an analysis of the Bayesian dynamic programming (BDP) equations, our main result shows that BDP-optimal decisions can be expressed as the sum of a myopic- optimal decision plus an ``exploration boost” that is proportional to the posterior variance-to-mean ratio of the demand.

36