2015 Informs Annual Meeting

MC50

INFORMS Philadelphia – 2015

MC50 50-Room 106A, CC Retail Supply Chain: From Demand Forecast to Order Fulfillment Sponsor: Manufacturing & Service Operations Management Sponsored Session Chair: Santiago Gallino, Tuck School of Business, 100 Tuck Hall, Hanover, NH, United States of America, santiago.gallino@tuck.dartmouth.edu 1 - How an e-Retailer can Profit from the Right Free Shipping Policy: A Model and Evidence Joseph (Jiaqi) Xu, The Wharton School, University of Pennsylvania, 3730 Walnut Street, Suite 500, Philadelphia, PA, United States of America, jiaqixu@wharton.upenn.edu, Gerard Cachon, Santiago Gallino We present a model of online retail profitability when customers purposely increase their order size to qualify for free shipping. While this behavior results in more sales, it also adds cost from less shipping revenue and more product returns. We find that free shipping threshold often decreases profitability and is effective only for retailers with high fulfillment cost relative to shipping revenue and with low probability of return. The model is applied to data from an online retailer. 2 - Can Supply Chain Flexibility Facilitate Information Sharing? Mohammad M. Fazel-Zarandi, PhD Candidate, Rotman School of Management, 105 St.George Street, Toronto, M5S 3E6, Canada, M.FazelZarandi10@Rotman.Utoronto.Ca, Oded Berman, Dmitry Krass We attempt to provide an explanation for a long-standing observation in supply chain management: while simple contracts cannot induce credible forecast sharing between different supply chain parties, firms often use them in practice, and exchange information through unverifiable communication. Using a stylized supply chain model, we show that if the reporting firm is uncertain about the receiving firm’s reaction to its report, it may truthfully share its private information in equilibrium. 3 - Improving Color Trend Forecasting using Social Media Data Youran Fu, PhD Student, The Wharton School, 3730 Walnut St, Philadelphia, PA, United States of America, youranfu@wharton.upenn.edu, Marshall Fisher We partnered with a leading apparel retailer to investigate how to use social media data to improve fashion color trend forecasting. We find that using fine- grained Twitter data and a Google search volume index to predict style-color sales three months out reduces forecast error by 11% compared to conventional methods. 4 - Wisdom of Crowds: Forecasting using Prediction Markets Ruomeng Cui, Assistant Professor, Indiana University, 309 E. Tenth Street, Bloomington, IN, 47401, United States of America, cuir@indiana.edu, Achal Bassamboo, Antonio Moreno-Garcia Prediction markets are virtual markets created to aggregate predictions from the crowd. We examine data from a public prediction market and internal prediction markets run at three corporations. We study the efficiency of these markets in extracting information from participants. We show that the distribution forecasts, such as sales and commodity prices predictions, generated by the crowds are perfectly calibrated. In addition, we run a field experiment to study drivers of forecast accuracy. Dynamic Contracts in Operations Management Sponsor: Manufacturing & Service Operations Management Sponsored Session Chair: Hao Zhang, Associate Professor, University of British Columbia, Sauder School of Business, Vancouver, BC, V6T1Z2, Canada, hao.zhang@sauder.ubc.ca 1 - Optimal Long-term Supply Contracts with Asymmetric Demand Information Wenqiang Xiao, Associate Professor, New York University, Stern School of Business, 44 West Fourth Street, 8-72, New York, NY, 10012, United States of America, wxiao@stern.nyu.edu, Ilan Lobel We consider a manufacturer selling to a retailer with private demand information arising dynamically over an infinite time horizon. We show that the manufacturer’s optimal dynamic long-term contract takes a simple form: in the first period, based on her private demand forecast, the retailer selects a wholesale MC51 51-Room 106B, CC

price and pays an associated upfront fee, and, from then on, the two parties stick to a simple wholesale price contract with the retailer’s chosen price. 2 - Dynamic Mechanisms for Online Advertising Hamid Nazerzadeh, University of Southern California, Bridge Memorial Hall, 3670 Trousdale Parkway, Los Angeles, CA, 90089, United States of America, hamidnz@marshall.usc.edu, Vahab Mirrokni I will discuss designing dynamic contracts for selling display advertising. I will show that under natural but rather restricted assumptions, the traditional reservation contracts can be revenue-optimal. I will also present the optimal mechanism in a general setting and discuss their practical implementations. 3 - Dynamic Short-term Contracts under Private Inventory Information and Backlogging Lifei Sheng, PhD Candidate, University of British Columbia, 2053 Main Mall, Vancouver, BC, V6T1Z2, Canada, Fay.Sheng@sauder.ubc.ca, Mahesh Nagarajan, Hao Zhang We study a setting where a supplier sells to a retailer facing random demand over multiple periods. At the beginning of each period, the supplier offers a one-period contract and the retailer decides his order quantity before the demand realizes. The retailer carries leftover inventory or backlogs unmet demand, which is unobservable by the supplier. We show interesting properties of the supplier’s optimal contract and study special cases when the problem is tractable. 4 - Structures of Optimal Dynamic Mechanisms Alexandre Belloni, Professor Of Decision Sciences, Duke University, 100 Fuqua Drive, Duke University, Durham, NC, 27708, United States of America, abn5@duke.edu, Peng Sun, Bingyao Chen Consider a principal procures up to one unit of a product/service in every period from an agent who is privately informed about its marginal production cost in each period. We identify regularity conditions on the distribution of private information under which the optimal contracts offer at most two different procurement levels depending on the newly reported cost. Our results rely on “dynamic virtual valuation,” a generalization of the Myersonian virtual valuation in the static setting. Chair: Aly Megahed, Research Staff Member, IBM Research, 650 Harry Road - Office D3-428, San Jose, CA, 95120, United States of America, aly.megahed@us.ibm.com 1 - Operations Research and Analytics Solutions for it Service Providers Aly Megahed, Research Staff Member, IBM Research, 650 Harry Road - Office D3-428, San Jose, CA, 95120, United States of America, aly.megahed@us.ibm.com, Hamid Reza Motahari Nezhad, Peifeng Yin, Taiga Nakamura Large IT service providers compete to win highly-valued outsourcing IT deals via submitting proposals to potential clients. In this talk, you will learn about some of the analytics and OR work done for managing such complex service engagements. A case management approach that analyzes costs and prices of deals in preparation will be presented. Additionally, a predictive analytics tool for identifying the influential factors on the outcome of deals will be shared. 2 - Measuring Cloud Services Profitability Ray Strong, Impact Of Future Technology, IBM Research, 650 Harry Road, San Jose, CA, 95120, United States of America, hrstrong@us.ibm.com, Jeanette Blomberg, Sunhwan Lee, Anca Chandra, Pawan Chowdhary, Susanne Glissmann, Robert Moore The costs of providing cloud services are not easily attributable to revenue. We present a complex modeling approach to understanding the profitability of individual service offerings and individual service contracts. We explore ways of creating long running models of cloud service performance in spite of the month- to-month and pay-for-use nature of many cloud contracts. We suggest an approach to estimating the total current value of a cloud service contract to a vendor. MC52 52-Room 107A, CC Analytics for IT Services Sponsor: Service Science Sponsored Session

222