2015 Informs Annual Meeting

MA03

INFORMS Philadelphia – 2015

2 - New Trends in Perence Modeling of Adversary Decisions Ali Abbas, Professor of Industrial and Systems Engineering and Public Policy and Director of Create, University of Southern California, 3710 McClintock Avenue, RTH 314, Los Angeles, CA, United States of America, aliabbas@price.usc.edu This talk will discuss the need for new models of preferences in both competitive and cooperative games. Simulation results and videos of cooperative autonomous vehicles will also be presented using new models of preferences.

22 Batterymarch St., Boston, MA, United States of America, gerner_mark@bah.com In this paper we present a methodology leveraging natural language processing and machine learning techniques to estimate the reputational and financial contribution from customer social media conversation, customer ratings, and associated comments from multiple online travel sites. 2 - Efficient Community Partition Algorithm in Networks Jiaofei Zhong, CSUEB, Dept. of Comp Sci,, 25800 Carlos Bee Blvd, Hayward, CA, United States of America, fayzhong08@gmail.com, David Haley, Ehsan Kamalinejad One fundamental problem in analyzing complex big data sets is the task of classification of the data. Community partitioning plays a crucial role in data analysis of scientific, social, and technological networks. As the study of isoperimetric inequalities is a well-explored field, it is possible to extend specific mathematical theory to its equivalent form in data clustering. We propose an efficient community partition algorithm to analyze the relationships among data via the network topology. 3 - Topic Dependent Edge Importance Measures in Social Media Platforms George Michailidis, University of Florida, 1 University Ave, Gainesville, FL, United States of America, gmichail@umich.edu Social media platforms produce large amounts of both structured and unstructured data. A key question for such platforms is to identify important interactions between nodes in the corresponding user network. we address this problem by using a stochastic model of interacting counting processes on a graph, so that topic dependent interactions can also be identified. We illustrate the results of our model on a US Senators Twitter data set. 4 - Role of Social Media in Healthcare via Analytics Sinjini Mitra, Assistant Professor, California State University, Fullerton, ISDS Department, 800 N State College Blvd, Fullerton, CA, 92831, United States of America, smitra@exchange.fullerton.edu The advance of computing resources and increased availability of large amounts of data in the recent decade has made it possible to use extensive analytics for effective decision-making in the healthcare industry. Based on a member survey of a large health plan, we identify factors (demographic, clinical and technological) that are significantly associated with member interest in adopting social and mobile media for obtaining health information via predictive and descriptive analytics. 5 - Time Geography Based Mobility Measures for Geo-tagged Twitter Data Mohsen Parsafard, University of South Florida, 4202 E. Fowler Avenue ENG 214, Tampa, Fl, 33620, United States of America, parsafard@mail.usf.edu, Guangqing Chi, Xiaopeng Li Social media data present tremendous opportunities for studying individuals’ travel behaviors. In this study, we propose a set of fundamental measures to quantify the bounds of an individual’s spatial and temporal activity range. We further develop an interpolation approximation method to improve the computation efficiency of these measures. Our results reveals an interesting pattern of people’s traveling and tweeting behavior where the proposed measures follow a power-law distribution. Financial Engineering Sponsor: Financial Services Sponsored Session Chair: Xuefeng Gao, Assistant Professor, The Chinese University of Hong Kong, xfgao@se.cuhk.edu.hk 1 - Mean Field Game with Singular Controls Joon Seok Lee, UC Berkeley, 2033 Haste St. #313, Berkeley, CA, 94704, United States of America, ljshope@berkeley.edu, Xin Guo We introduce a mean field game framework with singular controls. To solve this singular control problem with multiple agents, we derive the Fokker-Planck equation for the singular control, which is a generalization of the mean field game with regular controls. Both single controls of a bounded velocity and of a finite variation will be discussed. Finally, we will present some applications to optimal execution and systemic risk. 2 - Algorithmic Trading under the Effects of Volume Order Imbalance Ryan Donnelly, EPFL, Quartier UNIL - Dorigny, Extranef 214, 1015, Lausanne, Switzerland, ryan.donnelly@epfl.ch Shortcomings of some order book models are noted with motivation provided by data from the NASDAQ. The influence of volume order imbalance on order book dynamics is incorporated into a model which allows the agent to adjust their strategy based on an easily observable quantity. The imbalance allows the agent to MA06 06-Room 306, Marriott

MA03 03-Room 303, Marriott

Teaching Modern Project Management Cluster: Scheduling and Project Management Invited Session

Chair: Nicholas G. Hall, The Ohio State University, Fisher College of Business, Columbus, OH, United States of America, hall.33@osu.edu 1 - Modern Project Management Curriculum Ted Klastorin, Professor, University of Washington, Foster School of Business, Box 353226, Seattle, WA, 98195-3226, United States of America, tedk@u.washington.edu Empirical evidence has documented the failure to adequately manage many complex projects, including IT and new product development projects. At the same time, the need to successfully manage large and risky projects has never been greater. As a result, the need for effectively educating students in the project management (PM) area is critical. In this talk, I will explore the main directions and concepts that should be included in a PM curriculum and how this differs from current courses. 2 - Designing a Project Management Game Enno Siemsen, Associate Professor, University of Minnesota, As a capstone event in my project management class, I have designed a game to capture organizational dynamics in the context of a project management organization. Teams in the game form a hierarchy, with players taking the role of Vice Presidents, Project Managers or Resources. Having different incentives, these three types of roles need to learn to cooperate to see their projects to completion. 3 - Everything is a Project Nicholas G. Hall, The Ohio State University, Fisher College of Business, Columbus, OH, United States of America, hall.33@osu.edu This talk describes the development of an MBA course on project management that is the most popular elective at Fisher College of Business. The course uses various teaching methods - games and group activities, graded in-class problem solving exercises, guest speaker presentations with hands-on activities, HBS simulations, case reports with student presentations, along with traditional lecture and class discussion. The course currently enrolls students from seven graduate programs across campus. 4 - Teaching a Quantitative Approach to Project Management 321 19th Ave S, Minneapolis, MN, 55455, United States of America, siems017@umn.edu I will report on my course “Project Management – A quantitative approach”. The course is an elective in the third (and final) year of the undergraduate program in Management and Technology at TUM School of Management, Germany. The course covers a number of quantitative topics ranging from operational to strategic project management. I will report on the content of the course, pedagogical concepts used and feedback received from the students. MA05 05-Room 305, Marriott Applying Advanced Analytics to Social Media data Cluster: Social Media Analytics Invited Session Chair: Mohsen Parsafard, University of South Florida, 4202 E. Fowler Avenue ENG 214, Tampa, Fl, 33620, United States of America, parsafard@mail.usf.edu 1 - Estimating Social Media’s Financial Contribution to the Hospitality Sector Mark Gerner, Sr. Lead Economic Scientist, Booz Allen Hamilton, Rainer Kolisch, Technische Universität München, TUM School of Management, Arcisstraße 21, Munich, Germanyrainer.kolisch@wi.tum.de

146