2016 INFORMS Annual Meeting Program

SA48

INFORMS Nashville – 2016

3 - A Dynamic Clustering Approach To Data-driven Assortment Personalization Fernando Bernstein, Duke University, fernando@duke.edu Sajad Modaresi, Denis R. Saure A retailer faces heterogeneous customers with initially unknown preferences. The retailer can personalize assortment offerings based on available profile information; however, users with different profiles may have similar preferences, suggesting that the retailer can benefit from pooling information among customers with similar preferences. We propose a dynamic clustering approach that adaptively adjusts customer segments and personalizes the assortment offerings to maximize cumulative profit. 4 - Assortment Rotation And The Value Of Concealment Kris Johnson Ferreira, Harvard Business School, kferreira@hbs.edu, Joel Goh The frequency at which retailers change their assortment varies widely across fashion retailers. Some retailers choose to sell products simultaneously throughout the season, whereas others choose to sell products sequentially, requiring that the consumer make a purchase decision before seeing the subsequent products for sale. By offering products sequentially, retailers can introduce uncertainty in consumer choice that affects purchase decisions. We develop a consumer choice model and finite-horizon stochastic dynamic program to study when this uncertainty is advantageous for a retailer: a phenomenon we refer to as the retailer’s value of concealment. Social Media Analysis I Invited: Social Media Analytics Invited Session Chair: Chris Smith, Air Force Institute of Technology, 2950 Hobson Way, 2950 Hobson Way, Wright-Patterson AFB, OH, 45433, United States, cms3am@virginia.edu 1 - User Reward Programs In Online Social Media Fouad H Mirzaei, Santa Clara University, Unit 3, 559 Alviso St, Santa Clara, CA, 95050, United States, fhm.phd@ivey.ca, Fredrik Odegaard, Xinghao Yan Online social media (OSMs) have become a popular and growing Internet phenomenon, as exemplified by the millions of followers of websites like YouTube, Twitter, and Facebook. Given the Internet’s ease of access and the high degree of competition to attract users to these sites, a question arises as to whether OSMs should develop revenue-sharing programs as a way to reward their contributing users. We present an ex ante asymmetric duopoly OSM game, where heterogeneous users are either active or passive with respect to each OSM. In this study, we explore how online users’ actions and perspectives impact the outcome of the competition among OSMs. 2 - Research On The Influence Of Microblog Advertising Of Theatre Chain On Its First Week Box Office Revenue Jiayin Qi, Shanghai University of International Business and Economics, Shanghai, 100876, China, qijiayin@139.com, Jiaqi Liu With the participation of enterprise in social network, a question arises of how enterprise can gain more real profit from social network advertising. This article analyzes the relationships among contents of enterprise’s online post, consumer’s participation on microblog, and short-term product sales. Taking movie market as research set, this research finds that short-term product sales is positively influenced by the information quantity of enterprise’s post, and the influence is mediated by the “repost” of other users of Sina microblog. The mechanism examined in this research on the influence of microblog advertising on short-term sales can be guidelines of social network advertising. 3 - Social Media Use And New Product Development Performance Debasish N Mallick, Associate Professor, University of St. Thomas, Opus College of Business, 1000 La Salle Avenue # TMH 443, Minneapolis, MN, 55403, United States, dnmallick@stthomas.edu Use of social media is becoming increasingly popular in new product development (NPD). Yet, the performance impact of social media use in NPD remains inconclusive. Using a cross industry survey of new product development projects, we explore the factors affecting the relationship between social media use and NPD performance. SA48 210-MCC

2 - Optimal Dynamic Product Development And Launch For A Network Of Customers Nur Sunar, UNC, nur_sunar@kenan-flagler.unc.edu John Birge, Sinit Vitavasiri We consider a firm that dynamically chooses its effort to develop a product for a network of customers represented by a general connected graph. In addition to dynamically choosing its development effort, the firm chooses when to launch or abandon the product. If the firm launches the product, the firm also chooses a selling price, a promotional price and a target customer to offer promotion. Once the target customer adopts the product, the product dynamically diffuses over the customer network based on the topology of the graph and the selling price. In a continuous-time setting, we explicitly solve the firm’s jointly-optimal development, launch and post-launch strategies for any connected network. 3 - Quantity Pre-commitment And Cournot Equivalence Amr Farahat, Washington University-St. Louis, Campus Box 1133, We study a two-stage oligopolistic competition game, called the Quantity Pre- Commitment game, in which firms compete on quantity in the first stage and then compete on price in the second stage. This game is compared to a single- stage Cournot game, in which firms compete on the quantity only and the prices are set to clear the market. We show an equivalence result that an equilibrium of the Quantity Pre-Commitment game coincides with an equilibrium of the Cournot game, under certain conditions. The conditions that we identify are more general than those of specific models used in the seminal papers in the literature. 4 - A Stochastic Model For Pricing In Reverse Supply Chains Elif Akcali, University of Florida, Dept of Industrial and Systems Engineering, 303 Weil Hall PO Box 116595, Gainesville, FL, 32611-6595, United States, akcali@ise.ufl.edu, Sila Cetinkaya, Yi Zhang We address channel coordination issues in a two-echelon reverse supply chain that consists of a collector and a manufacturer. We develop stochastic models to maximize the manufacturer’s and collector’s profits in a game-theoretic framework. We develop an effective mechanism to coordinate manufacturer’s and collector’s decisions. SA47 209C-MCC Topics in Assortment Planning and Consumer Choice Sponsored: Revenue Management & Pricing Sponsored Session Chair: Kris Johnson Ferreira, Harvard Business School, Boston, MA, United States, kferreira@hbs.edu 1 - A Data-driven Approach To Customer Segmentation Ashwin Venkataraman, New York University, 719 Broadway, 7th Floor, New York, NY, 10003, United States, ashwin@cs.nyu.edu Srikanth Jagabathula, Lakshminarayanan Subramanian We propose a new “model-based” projection technique for segmenting customers based on partial observations for each customer. We suppose that data are available in the form of categorial responses for on a collection of n variables for each customer. This unified representation allows one to combine diverse signals (clicks, demographics, purchases, etc.) to obtain accurate segmentation. Our method relies on a combination of model-based projections and matrix completion techniques to obtain the clusters. We theoretically and empirically show how our method is superior to existing benchmarks. 2 - Analysis Of Choice Models: A Welfare-based Framework Xiaobo Li, University of Minnesota, Minneapolis, MN, 55414, United States, lixx3195@umn.edu, Guiyun Feng, Zizhuo Wang We propose a framework for discrete choice models through a welfare function. The framework provides a new way of constructing choice models. It also provides great analysis convenience for establishing connections among existing choice models. We define a new property in choice models: substitutability/complementarity and study conditions for a choice model to be substitutable. We show that our framework is flexible in this property, which is desirable in capturing practical choice patterns. 1 Brookings Drive, St. Louis, MO, 63130, United States, farahat@wustl.edu, Woonghee Tim Huh, Hongmin Li

33