Informs Annual Meeting 2017

TA02

INFORMS Houston – 2017

2 - Domain Dependent Attitudes Veronica Roberta Cappelli, PhD Student, HEC Paris, Jouy en Josas, France, veronica.cappelli@hec.edu Many everyday decisions can be framed as choices between streams of multicriteria alternatives. At the same time, there is by now substantial evidence that decision makers may have domain-specific attitudes toward outcomes. In particular, different categories of outcomes may be discounted differently and associated with different levels of risk aversion. This work aims at providing an axiomatized model of choice between streams of multicriteria alternatives. Our objective is to allow for an evaluation functional that takes into account the fact that, not only utility, but also discounting may be attribute, or domain, dependent. 3 - Accelerated Kriging for Global Sensitivity Analysis Xuefei Lu, Bocconi University, Via Sarfatti 25, Milan, 20136, Italy, xuefei.lu@phd.unibocconi.it, Emanuele Borgonovo, Lorenzo Andrea Rosasco, Alessandro Rudi In global sensitivity analysis, kriging is commonly applied as a metamodeling technique, especially when the analyst is dealing with time-consuming computer codes. We study an improved kriging improving estimation with an acceleration procedure coming from Machine Learning. We apply this method to global sensitivity analysis and compare the results with standard kriging. 4 - Information Density in Decision and Sensitivity Analysis Emanuele Borgonovo, Bocconi University, Bocconi University, Via Sarfatti 25, Milano, 20136, Italy, emanueleborgonovo@unibocconi.it, Gordon B. Hazen, Victor Richmond R.Jose This work discusses the use of the notion of information density in decision and sensitivity analysis. 5 - On the Relationship Between Safety and Decision Significance Alessandra Cillo, Bocconi University, Via Roentgen 1, Milan, 20136, Italy, alessandra.cillo@unibocconi.it, Emanuele Borgonovo, Curtis L. Smith Risk analysts are often concerned with identifying key safety drivers, i.e., the systems, structures and components (SSCs) that matter the most to safety. SSCs importance is assessed both in the design phase and in the implementation phase using the same importance measures. However, in a design phase it would be necessary to appreciate whether, the failure/success of a given SSC can cause the overall decision to change from accept to reject. This work addresses the search for the conditions under which SSCs which are safety significant are also decision significant. To address this issue, the work proposes the notion of teta-importance measure. 310B Behavioral Issues in Counter-Terrorism Decisions Sponsored: Decision Analysis Sponsored Session Chair: Heather Rosoff, University of Southern California, Los Angeles, CA, 90024, United States, rosoff@usc.edu Co-Chair: Gilberto Montibeller, Loughborough University, Loughborough University, Loughborough, LE11 3TU, United Kingdom, g.montibeller@lboro.ac.uk 1 - Modeling Multi-target Defender-attacker Games with Quantal Response Attack Strategies Jun Zhuang, University at Buffalo, SUNY, 317 Bell Hall, Buffalo, NY, 14260, United States, jzhuang@buffalo.edu, Jing Zhang Due to the growing interest in incorporating behavior models within thedefender- attacker game literature, the perfect rationality assumption of adversary has been relaxed. We study four multi-target defensive resource allocation in defender- attacker games by using quantal response model, in which the attacker might be bounded rational. We compare the our model results with the traditional game theoretic model where the attacker behaves rationally. We studied the impacts of the attacker’s rationality level on the defender’s optimal defense strategies. This paper provides some novel insights to defensive resource allocation when considering the attacker’s bounded rationality. 2 - A Roadmap for OR Research in Homeland Security Detlof von Winterfeldt, USC, 3710 McClintock Ave, RTH 316A, Los Angeles, CA, 90089-3926, United States, detlof@aol.com On the occasion of 15th anniversary of 9/11, we will summarize the evolvement and analyze strengths and weaknesses of OR methods in homeland security, in particular in decision and risk analysis, optimization, game theory as well as in simulation and stochastic methods. On the other hand, we will identify in a survey the needs of current key decision makers in homeland security. Finally, we will bring the status quo in theory and the practical needs together in order to develop a roadmap for research on OR methods in counterterrorism in the future. TA02

3 - Public Response to the Security Threat to Aviation Richard S. John, University of Southern California, Dept of Psychology MC 1061, Los Angeles, CA, 90089-1061, United States, richardj@usc.edu, Heather Rosoff Important to the effectiveness of airport security measures is public response to the implemented policies. We will present three studies that have assessed public reaction to varying aspects of the security threat to aviation. The first is a longitudinal study looking at the psychological effects of the events of 9/11 over 5 years. The second study examines how travelers value the principle of equal protection by quantifying their willingness to sacrifice to avoid different screening procedures. The third study looks at public perception of traditional airport security schedules that search everyone versus randomized security schedules that randomly deploy security measures. 4 - Understanding Terrorist Attacks with Learning Models Gilberto Montibeller, Loughborough University, School of Business & Economics, Loughborough, LE11 3TU, United Kingdom, g.montibeller@lboro.ac.uk, Johannes Jaspersen In this paper we adopt the perspective of the terrorist group as an economic agent learning from reinforcement and calibrate different learning models to study the target selection of terrorists using empirical data. Terrorists display the power law of learning and discount prior information, but show no tendency to have an aspiration level or reference point. Our results show learning models from laboratory experiments in behavioral economics to be applicable to naturally occurring human conflicts and let us draw implications for counterterrorism strategies. 5 - A Hybrid Spatio-temporal Model for Wildlife Poaching Prediction Evaluated through a Controlled Field Test Shahrzad Gholami, PhD Student, University of Southern California, Los Angeles, CA, 90089, United States, sgholami@usc.edu, Milind Tambe Worldwide, conservation agencies employ rangers to protect conservation areas from poachers. However, agencies lack the manpower to have rangers effectively patrol these vast areas frequently. While past work has modeled poachers’ behavior so as to aid rangers in planning future patrols, those models’ predictions were not validated by extensive field tests. We present a hybrid spatio-temporal model that predicts poaching threat levels and results from a five-month field test of our model in Uganda’s Queen Elizabeth Park. Invited: Tutorial Invited Session Chair: Jiming Peng, University of Houston, Houston, TX, 77204, United States, jopeng@Central.uh.edu Chair: Rajan Batta, University at Buffalo (SUNY), 410 Bell Hall, Buffalo, NY, 14260, United States, batta@buffalo.edu 1 - Dynamic Ridesharing Fernando Ordonez, DII, Univeridad de Chile, Santiago, Chile, fordon@dii.uchile.cl, Maged M.Dessouky Recent technological developments such as GPS, mobile devices and increases in data storage and computation capacity have greatly enhanced the communication capabilities of travelers, facilitating ridesharing in real-time. This opportunity has created a new ridesharing industry built on making use of the unused vehicle capacity moving about on the roads. There are however still important barriers for widespread dynamic ridesharing adoption. It therefore becomes important to better understand the problems and challenges of ridesharing, creating the need for novel research that explicitly takes into account dynamic ridesharing. In this tutorial we review recent research on new vehicle routing models, cost sharing mechanisms, and planning models that incorporate ridesharing. TA03A Grand Ballroom A Energy in Applied Probability Sponsored: Applied Probability Sponsored Session Chair: Bert Zwart, Eindhoven, 5629RD, Netherlands, Bert.Zwart@cwi.nl 1 - Estimating Line Failure Probability in Power Grids under Uncertainty Tommaso Nesti, CWI, Amsterdam, Netherlands, TNesti@cwi.nl The advent of renewable energy has huge implications for the control of power TA03 310C Dynamic Ridesharing

268