Informs Annual Meeting 2017

MC54

INFORMS Houston – 2017

MC53

4 - Social Media Integration and E-commerce Platform Performance: A Randomized Field Experiment Ni Huang, Arizona State University, Tempe, AZ, United States, ni.huang@asu.edu, Tianshu Sun, Pei-yu Chen, Joseph Golden E-commerce platforms can integrate with social media to let users directly comment on product pages. Such integration can convey credible information but may also hinder product sales due to less control over user comments. Thus, it is not clear whether an ecommerce platform should embrace such integration. We conduct a randomized experiment with a large ecommerce platform to examine the impact of social media integration on users’ shopping behaviors. We find customers in the treatment, who see product pages with Facebook comment integration, are significantly more likely to place an order. We further explore heterogeneous treatment effects and find them aligned with social learning mechanism.

361F Opportunities and Issues of Shared Mobility Services Sponsored: TSL, Intelligent Transportation Systems (ITS) Sponsored Session Chair: Mohammad Abdollahi, Wayne State University, 4815 Fourth Street, Room 1067, Detroit, MI, 48202, United States, abdollahi@wayne.edu 1 - Dynamic Ride Pooling. Benefiting from Last Mile Opportunity Mohammad Abdollahi, PhD Student, Wayne State University, 4815 Fourth Street, Room 1067, Detroit, MI, 48202, United States, abdollahi@wayne.edu, Kai Yang This paper is addressing the design of DRT system where real-world practical constraints are considered in providing customized vehicle routing and scheduling. Designing this system allows for dispatch operators to quickly explore tradeoffs between level-of-service and operating costs. We have developed a constraint programming based benders decomposition algorithms for this system. Using the methodology developed in this paper we expect not to have just cost benefits, but also improved quality of service and the reduction in total vehicle- kilometers traveled which leads to environmental benefits. 2 - The Effect of New Shared Mobility Services on the Transportation Network Mona Asudegi, Lead Technologist, Booz Allen Hamilton, 20 M St. SE, #1000, DC, 20003, United States, asudegi_mona@bah.com, Sara Sarkhili Mobility market is rapidly changing due to changes in technology, information availability, and social trends. More people are using these new forms of mobility services for their day-to-day transportation. It is of interest to see how these new forms of services are affecting the transportation networks; are they taking more customers away from transit or are they reducing the single occupant vehicles on the road? This study models, simulates, and investigates difference scenarios of shared used mobility services, for a specific region, to determine their effects on traffic network performance measures. 3 - A Date-driven Analysis of the Impact Exerted on Government Regulations in Taxi Industry by E-hailing Service Ziyang Guo, Sparkzone Research Group, Room6, Yard 7, Fenzi Hutong, Xidan North, Street, Xicheng District, Beijing, China, Beijing, China, 1872371084@qq.com, Yide Zhao, Yinghao Jia Government has mainly regulated the traditional taxi market from four perspectives: taxi number, price and quality of service, as well as standard working time of drivers. However, the emergence of E-hailing service has posed a great challenge for the traditional industry. This study, emphasizing on the four aspects above, aims to capture the impact of E-hailing service on traditional market based on data-driven approaches. Primarily focusing on the flexibility and elasticity of the E-hailing service, we propose a model that takes into account the influence exerted on the equilibrium position of the taxi market, thereby optimizing regulation policies for administration. 362A Syngenta Crop Challenge in Analytics Invited: Agricultural Analytics Invited Session Chair: Robin Lougee, IBM Research, Yorktown Heights, NY, 10598, United States, rlougee@us.ibm.com 1 - A Hierarchical-ensemble of Machineries to Optimize the Choice of Soybean Varieties Durai Sundaramoorthi, Washington University in Saint Louis, 10352 Conway Road, Saint Louis, MO, 63131, United States, Selecting soybean varieties for planting is an important decision that has significant implications for the yield of a farm. With many soybean varieties available along with data on yield performance collected over several years at various farm locations, the seed-mix selection is a highly intriguing decision to modern day farmers and seed retailers. To aid soybean-mix selection, this work describes and evaluates a hierarchical-ensemble of machine learning and optimization methods which chooses soybean varieties to obtain optimal yield. MC54 dsundaramoorthi@gmail.com, Lingxiu Dong, Iva Petrova Rashkova, Piruthiviraj Sivaraj

MC52

361E Energy Contributed Session

Chair: Zhi Zhou, Argonne National Laboratory, 9700 South Cass Avenue, Bldg 221, Argonne, IL, 60439, United States, zzhou@anl.gov 1 - Efficient Pricing Methodologies for Integration of Distributed Technology. J.M.Omar Khaiam, PhD Candidate, University of Auckland, Auckland, New Zealand, jkha088@aucklanduni.ac.nz, Anthony Downward With the rapid development of solar PV and holdhouse and grid-scale battery technology, the distribution network facing a number of challenges. In this presentation we discuss a model that determines how batteries should be installed in the distribution network (either by households, or by the distribution network owner), and how changes to the distribution tariff structure may induce efficient investment choices. We examine whether the economic ‘death-spiral’ for distribution assets can be avoids using efficient market signals. 2 - A Mixed Complementarity Problem Extension to Find Near Equilibrium Electricity Prices for Non-convex Unit Commitment Models Mehrdad Pirnia, University of Waterloo, 200 University Ave, West, Waterloo, ON, N2L3G1, Canada, mpirnia@uwaterloo.ca, Hassan Shavandi, John David Fuller We propose a realistic unit commitment model, based on an extension of the mixed complementarity problem method, to approximate the minimization of the opportunity cost of electricity market players, including generators, consumers and transmission line operators. The opportunity costs arise due to the nonconvexities of binary variables for the on/off status of generators. The solution of the proposed model reduces the opportunity cost of generators, compared to the standard maximum social welfare calculation for unit commitment, and it provides near equilibrium electricity market prices and generation dispatch quantities. 3 - Investments in Power Generation and Transmission: The Effect of Capacity Procurement Kazuya Ito, Tokyo University of Science, 2641 Yamazaki, Noda-shi, Chiba, 278-8510, Japan, 7416605@ed.tus.ac.jp, Ryuta Takashima, Makoto Tanaka The penetration of renewable energy has induced a decrease in capacity factors and a decommissioning for existing generations, and a reduction in new investments. This problem implies a fear for the shortage of capacity in the electricity market. Thus, in order to meet the capacity in the market, policymakers implement various policies for capacity procurements. In this work, we analyze investments in power generation and transmission by means of real options theory. The ISO decides the investment timing by maximizing social welfare whereas a generation firm invests by maximizing the own profit. Especially, we examine the effect of capacity procurement for the ISO on the investment decisions. 4 - Energy-water Nexus Modeling and Analysis: From Cooling Water Efficiency and Electric Grid Operation Perspectives Zhi Zhou, Argonne National Laboratory, 9700 South Cass Avenue, Bldg 362, Argonne, IL, 60439, United States, zzhou@anl.gov, Ying Wang, Getnet Betrie, Eugene Yan Most electricity generation needs large amounts of cooling water, which is extensively demanding in hot and arid areas. We propose a model to estimate the water usage (including water withdraw and consumption) in the power plants operation based on practical operation data. The water usage model reflects the impacts of environment temperature, electricity generation and cooling technologies, et. al. The cooling efficiency and water availability constraints are integrated into the power system operation model. Results show that water availability and temperature have significant impact on power grid economics.

221