2015 Informs Annual Meeting

WA53

INFORMS Philadelphia – 2015

2 - Inventory Allocation in Omni-channel Retailing Alexander Huebner, Associate Professor, Catholic University Eichstaett-Ingolstadt, Auf der Schanz 49, Ingolstadt, 85049, Germany, alexander.huebner@ku.de, Heinrich Kuhn, Andreas Holzapfel Omni-channel retailers need to allocate inventories to their stores and the warehouse for online fulfillment. The objective is to reduce for all channels operational replenishment costs, stock-out costs and margin losses for overaged inventory. We develop a decision model for inventory allocation and setting the end-season discounts. The problem is solved with stochastic dynamic programming. We show insights from a case study with a German fashion retailer, where the model is applied. 3 - Vendor Influence on Inventory Adjustments Daniel Corsten, IE Business School, Calle Maria de Molina 12 Bajo, Madrid, 28006, Spain, daniel.corsten@ie.edu, Shivom Aggarwal Vendor-side factors have been overlooked in the literature on shrinkage due to intractability. Using multi-store longitudinal data from a US retailer we investigate antecedents of shrinkage and how they affect store performance. Our holistic framework will contribute to extant literature on retail operations. 4 - Efficient Algorithm for Assortment Planning with Limited Shelf Space Chun-miin Chen, Assistant Professor, Bucknell University, 313 Taylor Hall, 701 Moore Ave., Lewisburg, PA, 17837, United States of America, cmc052@bucknell.edu, Zhaolin Li We study the impact of limited shelf space on assortment planning in a single- period model. As the shelf-space constraint makes the optimization problem NP-complete, we investigate a comprehensive measure which enables efficient identification of the variants to be added into the assortment and efficient allocation of the available shelf space. 5 - An Analytics Framework for the Retail Shelf Space Management Anurag Agarwal, Professor, University of South Florida, 8350 N Tamiami Tr, Sarasota, FL, 34243, United States of America, agarwala@sar.usf.edu, Ramakrishna Govindu, James Curran Due to advancements in information technology, retailers are collecting a lot of data and trying to optimize their limited shelf space. In this presentation, we propose an analytics framework that integrates predictive and prescriptive analytics for optimizing the retail shelf space. WA53 53-Room 107B, CC Behavioral Models in Operations Management Sponsor: Behavioral Operations Management Sponsored Session Chair: Xuanming Su, The Wharton School, University of Pennsylvania, Philadelphia, United States of America, xuanming@wharton.upenn.edu 1 - The Impact of Decision Rights and Long Term Relationships on Innovation Sharing Ruth Beer, Kelley School of Business, Indiana University, 1275 E 10th St, Bloomington, IN, 47405, United States of America, ruthbeer@indiana.edu, Stephen Leider We study a supplier’s incentives to share an innovation with a buyer when sharing the innovation increases efficiency but makes the supplier vulnerable to the buyer sharing it with other suppliers. We show, both theoretically and experimentally, that the supplier’s optimal decision depends on the length of the relationship and in particular, on how the buyer allocates decision rights among its employees. 2 - Linking Customer Behavior and Delay Announcements using a Probability Model Qiuping Yu, Assistant Professor, Indiana University, 1309 E. 10th Street, Bloomington, IN, 47405, United States of America, qiupyu@indiana.edu, Eric Webb, Kurt Bretthauer Service systems often offer announcements to customers about their anticipated delay. We empirically examine how announcements affect queue abandonment behavior using a duration model accounting for potential behavioral factors. Our results show announcements induce the reference effect and customers exhibit loss aversion. We also find evidence indicative of the sunk cost fallacy. We then provide insights for staffing and delay announcement policy accounting for observed behavioral factors.

3 - Trust, Social Networks, and Information Sharing Among Executives

Karen Zheng, MIT, 77 Massachusetts Avenue, Cambridge, MA, 02139, United States of America, yanchong@mit.edu, Emily Choi, Ozalp Ozer We experimentally study how trust and social networks influence forecast information sharing behavior among executives with an average 17 years of professional experience. We demonstrate an intricate interaction among trust preconditioned by prior experiences, trust measured from social network, and trust in supply chain information exchange. We show when trust from social network significantly impacts trust in the supply chain and the resulting information sharing efficiency. 4 - Behavioral Impact of Irrelevant Market Information on Buying Decisions

Kay-Yut Chen, Professor, University of Texas Arlington, 701 West Street, Arlington, TX, United States of America, kychen@uta.edu, Diana Wu

We study how market information such as past sales, current stock levels and stock-out probability influences purchase behavior. Experiments are conducted in which buyers, who are exposed to different information, evaluate trade-offs between the likelihood of out-of-stock and future price discounts. We found that individuals can be swayed by information that is non-informative and irrelevant. We develop a behavioral model that captures such behavioral reactions to explain the lab findings.

WA54 54-Room 108A, CC Resource Allocation Contributed Session

Chair: Marc Jansen, Phd Candidate, Judge Business School, University of Cambridge, Trumpington Street, Cambridge, United Kingdom, mcj32@cam.ac.uk 1 - Optimal Allocation of Conference Rooms to Meeting Requests Pawan Chowdhary, Software Research, IBM Research, 650 Harry Road, San Jose, CA, 95120, United States of America, chowdhar@us.ibm.com, Robert Moore, Susanne Glissmann, Sunhwan Lee, Ray Strong, Anca Chandra, Jeanette Blomberg We present an analytics driven solution that dynamically allocates the conference rooms based on time and other constraints. The approach initially assigns a conference room using greedy heuristic and later reassigns or reaffirms the room as responses from attendees arrive. We will show the results of both traditional and optimal approach along with algorithm. We will also discuss how we can leverage mobile to further enhance the solution and analytics to further improve the outcomes. 2 - Optimizing Campsites Accommodation and Prices Dasong Cao, Principal Scientist, Wyndham Exchange and Rental, 14 Sylvan Way, Parisippany, NJ, 07054, United States of America, dasong.cao@rci.com European vacation rental company offers package camping holidays, the accommodation includes mobile homes, lodges and tents. Each year, they put together a contracting plan, to decide which sites to choose to place accommodation units on and how many units of each type to offer on each site, and then a process to set the prices. We first built a mathematical model to pick optimal site location and unit mix, and then built an Yield Management System to set the prices dynamically. 3 - Managing Escalation: Support System Failure and Response Capacity Allocation Marc Jansen, PhD Candidate, Judge Business School, University of Cambridge, Trumpington Street, Cambridge, United Kingdom, mcj32@cam.ac.uk, Nektarios Oraiopoulos, Daniel Ralph Recent high profile IT system disruptions highlight the dependency of large client pools on continuous availability of equipment provided and maintained by a single vendor. At the onset of disruption, the scale of the disruption is typically unknown. This paper examines how contracting decisions between an IT vendor and multiple clients can enable efficient allocation of response capacity under imperfect information on the true nature of the disruption.

390