Informs Annual Meeting 2017

TB01

INFORMS Houston – 2017

Tuesday, 10:30 - 12:00PM

2 - Where do We Stand on Multi-objective Decision Making? Ali E. Abbas, Director, DECIDE Center, University of Southern California, OHE 310R, 3650 McClintock Ave, Los Angeles, CA, 90089, United States, aliabbas@usc.edu The construction of a representative multi-attribute utility function is is an essential step in the analysis of many decisions. This talk with discuss some advances in the field of multi-attribute utility (including graphical representations and connections with artificial intelligence). The talk will also discuss some misuses of the theory, and some subtleties and approaches that still persist. 3 - An Interactive Bayesian Method for Multicriteria Sorting Problems Canan Ulu, Georgetown University, McDonough School of Business, Operations and Information Management Area, Washington, DC, 20057, United States, cu50@georgetown.edu, Tom Shively We build a Bayesian learning model for the multicriteria sorting problem. 4 - Robust Multicriteria Decision Analysis Fabio Maccheroni, Universita Bocconi, Via Sapfath, 25, Milan, Italy, fabio.maccheroni@unibocconi.it, Veronica Roberta Cappelli, Salvatore Corrente, Salvatore Greco In MCDA, often an alternative can be represented by a vector of probabilities, its i-th component representing the distribution of scores of attribute i. Typically (Keeney and Raiffa, 1976), alternatives are evaluated by an expected additively separable utility. Yet, in many situations the DM’s utility is unknown to the DA: available data only leads to an incomplete ranking of alternatives. We provide necessary and sufficient conditions to represent this ranking by a family of additively separable utility functions, so that an alternative outranks another alternative if and only if its expected utility is greater than that of the other alternative for every utility in the representing family. Invited: Tutorial Invited Session Chair: Jiming Peng, University of Houston, Houston, TX, 77204, United States, jopeng@Central.uh.edu Co-Chair: Rajan Batta, University at Buffalo (SUNY), 410 Bell Hall, Buffalo, NY, 14260, United States, batta@buffalo.edu 1 - Quantitative Imaging System for Cancer Diagnosis and Treatment Planning: An Interdisciplinary Approach Teresa Wu, Arizona State University, Tempe, AZ, United States, Teresa.Wu@asu.edu During the past decade, with breakthroughs in systems biology, precision medicine has emerged as a novel paradigm that has transformed healthcare. Precision medicine is an approach for disease treatment and prevention that takes into account individual variability where medical imaging is a key component. This tutorial focuses on research investigating the roles of medical imaging in cancer diagnosis and treatment planning. While the cornerstone of the imaging research is mathematical and statistical modeling, the research has to take a multidisciplinary and systematic approach due to the nature of the problem. We offer a comprehensive review and discussion on four important components that form an imaging pipeline: imaging pre-processing, imaging feature extraction, feature dimensionality reduction and classification. To illustrate the clinical relevance, our in-house developed system, the imaging Multi-Texture Disease Diagnosis System (iMT-DDS) is presented with two clinical case studies, one on breast cancer diagnosis using contrast enhanced digital mammography imaging, and the other on cholangiocarcinoma using computed tomography imaging. The future directions of the imaging research are highlighted in the end. TB03 310C Quantitative Imaging System for Cancer Diagnosis and Treatment Planning: An Interdisciplinary Approach

TB01

310A Portfolio Decision Analysis Sponsored: Decision Analysis Sponsored Session Chair: Alec Morton, University of Strathclyde, Glasgow, G1 1XQ, United Kingdom, alec.morton@strath.ac.uk Co-Chair: Liesio Juuso, juuso.liesio@aalto.fi 1 - Out of Sample Comparison of SSD and Directionally SSD Constrained Portfolio Choice Nasim Dehghan Hardoroudi, Aalto University School of Business, Runeberginkatu 22-24, Chydenia (4th floor), Helsinki, 00100, Finland, nasim.dehghan.hardoroudi@aalto.fi In this paper we compare out-of-sample performance of second order stochastic dominance (SSD) and directionally SSD constrained portfolio optimization using stock market data of the US. When the market index is taken as benchmark, out- of-sample tests show that both SSD and DSSD constrained optimization with a variety of objective functions out-perform the benchmark in terms of average return, and DSSD based approach compares favorably against SSD based, given that risk aversion exhibited by the objective function is relatively mild. 2 - Sparse Dynamic Portfolios with Regret-based Selection David Puelz, University of Texas, 6309 Burns Street, Austin, TX, 78752, United States, david.puelz@utexas.edu This paper considers portfolio construction in a dynamic setting. We present a new decision theoretic approach based on a loss function comprised of utility and portfolio complexity components. These components are related by an unknown tradeoff parameter, and we develop a novel regret-based criterion for selecting the tradeoff parameter to construct optimal sparse portfolios over time. We demonstrate the procedure under a variety of modeling and preference scenarios using data from exchange traded funds. 3 - Allocation Rules for Global Donors Alec Morton, University of Strathclyde, Management Science, University of Strathclyde, Glasgow, G1 1XQ, United Kingdom, alec.morton@strath.ac.uk, Ashwin Arulselvan, Ranjeeta Thomas, Peter C. Smith A vitally important part of ensuring that recent improvements in global health are sustained is financial aid from rich countries to poor ones. Aid donors must also ensure that countries build the financial capacity to deliver healthcare for their own population on a sustainable basis, and the allocation rules used by aid donors must reflect this. We present a game theoretic analysis of the relationship between a donor and a country. The donor has a healthcare related mission and the country cares about healthcare but also about other things. We show how our model produces both insight and operationalisable rules for guiding aid donation. 310B Multicriteria Decision Making Sponsored: Decision Analysis Sponsored Session Chair: Canan Ulu, Georgetown University, Washington, DC, 20057, United States, cu50@georgetown.edu 1 - An Additive Model of Decision Making under Riskand Ambiguity Ying He, University of Southern Denmark, Campusvej 55, Odense, M, 5230, Denmark, yinghe@sam.sdu.dk, James S. Dyer, John C. Butler, Jianmin Jia We develop preference conditions to separate “value’, “risk” and “ambiguity” to obtain a descriptive, additive model of decision making under risk and ambiguity. This model explicitly captures the tradeoff between the magnitude of risk and the magnitude of ambiguity when making a choice over ambiguous lotteries. Combining this model with the standard risk-value model, we obtain a value- risk-ambiguity preference model. TB02

302