EURO Journal on Decision Processes最新文献

We propose an introduction to the use of incremental preference elicitation methods in the field of multiobjective combinatorial optimization. We consider three different optimization problems in vector-valued graphs, namely the shortest path problem, the minimum spanning tree problem and the assignment problem. In each case, the preferences of the decision-maker over cost vectors are assumed to be representable by a weighted sum but the weights of criteria are initially unknown. We then explain how to interweave preference elicitation and search to quickly determine a near-optimal solution with a limited number of preference queries. This leads us to successively introduce an interactive version of dynamic programming, greedy search, and branch and bound to solve the problems under consideration. We then present numerical tests showing the practical efficiency of these algorithms that achieve a good compromise between the number of queries asked and the solution times.

In this article, justification diagrams are introduced for structuring evidence to support conclusions that are reached from results of simulation studies. An industrial application is used to illustrate the use of the justification diagrams. Adapted from the Toulmin schema, the aim of justification diagram is to define a comprehensive, auditable and shareable notation to explain the results, the input data, the assumptions made and the techniques applied, to construct a cogent conclusion. Further, the dustification diagrams provide a visual representation of the argument that aims to corroborate the specified claims, or conclusions. A large part of this work is based on the application of the justification diagrams in the context of the European project, TOICA. The justification diagrams were used to structure all justifications that would be needed to convince an authority that a simulation process, and the associated results, upheld a particular conclusion. These diagrams are built concurrently in a product development process that accompanies the various stages of Verification and Validation (V&V) and where, for each design stage of V&V, argumentation is constructed by aggregating evidence and documents produced at this design stage.

This paper explores, through an application example, connections between argumentation and another type of methods often involved in decision problems, namely, multicriteria analysis. A novel argumentative analysis framework is proposed and applied to assess a short supply chain device for food aid, regarding different categories of criteria. The analysis leads to some feedback concerning argumentation systems.

The ratio bias refers to the tendency of individuals to judge probabilities expressed as ratios of large numbers as more likely than equivalent or even higher probabilities expressed as a ratio of small numbers. For example, the ratio bias effect occurs when a lottery offering a 9/100 chance of winning is preferred over a lottery that offers a 1/10 chance of winning. Although previous empirical research has found evidence for the ratio bias, the exact conditions under which this effect occurs are still unclear and there is a lack of rigor in distinguishing the ratio bias from other similar effects. In this article, besides providing a comprehensive and integrative literature review, we present the results of an experiment in which we extend previous research on the ratio bias by comparing deviations both in favor of low- and high-number alternatives, as well as allowing for indifference. Results indicate that a systematic deviation in favor of high-number alternatives does exist, but that the ratio bias must be clearly distinguished from a general tendency to indicate indifference. Concerning characteristics of the problem and the decision maker, we find significant influences of probability levels involved (the ratio bias occurs more frequently for low probabilities), and of gender (the bias occurs more often among female subjects).

Scoring rules are traditional techniques to measure the association between a reported belief and an observed outcome. The condition that a scoring rule is proper means that an agent maximizes his expected score when he reports a belief that equals his true belief. The implicit assumption that the agent is risk neutral is, however, often unrealistic, at least when the underlying agent is a human. Modern decision theories based on rank-dependent utilities, such as cumulative prospect theory, have been shown to be more effective at describing how human beings make decisions under risk and uncertainty. Traditional proper scoring rules are, however, incompatible with cumulative prospect theory because they fail to satisfy a property called comonotonicity. In this paper, we provide novel insights on why comonotonicity is crucial to make proper scoring rules indeed proper when eliciting beliefs from cumulative prospect theory agents. After suggesting strategies to create comonotonic proper scoring rules, we propose calibration procedures to obtain an agent’s true belief by removing the influence of the agent’s value function and weighting functions from his reported belief, when beliefs are elicited by means of comonotonic proper scoring rules.

For several reasons like benchmarking of MCDA methods, the MCDA community should be interested in the production of simulated multicriteria datasets based on real datasets. Our goal in this paper is to propose several methods to simulate these new multicriteria data from an existing dataset. Simulated data should be as similar as possible to the initial dataset, including the capture of specific structure in the initial dataset (if any). We propose here to study independent sample, PCA-based sample and copula-based sample and to determine which one best succeeds in generating new data on demand. The copula-based method seems the best one to reproduce specific links between criteria.$n$

Cholera outbreaks are quite common in the aftermath of natural or man-made disasters. Population displacement and overcrowding in conjunction with increased prevalence of malnutrition and degradation of sanitary conditions present the main drivers favoring cholera outbreaks in these settings. Although cholera is a vaccine-preventable disease, the implementation of mass vaccination campaigns remains still a difficult task in humanitarian emergencies. In this paper an attempt is made for identifying critical success factors as well as the possible interrelationships among them for successfully implementing cholera vaccination campaigns in humanitarian emergencies. Such factors are identified through systematically surveying the literature. Based on this survey and following experts’ responses relevant priorities are identified and the description and analysis of the interrelationships among these factors are given through the usage of the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method. According to the results of the analysis, sound coordination among the key-players involved, establishment of surveillance systems and mobilization of the target communities present the three most important factors while security issues and the general political context in which an immunization campaign is implemented are considered the most influential factors. The findings could be of significant value to those drafting contingency plans or implementing immunization campaigns in humanitarian emergencies.

Determining a fair price and an appropriate timescale to trade municipal debt is a complex decision. This research uses data informatics to explore transaction characteristics and trading activity of investment grade US municipal bonds. Using the relatively recent data stream distributed by the Municipal Securities Rulemaking Board, we provide an institutional summary of market participants and their trading behavior. Subsequently, we focus on a sample of AAA bonds to derive a new methodology to estimate a trade-weighted benchmark municipal yield curve. The methodology integrates the study of ridge regression, artificial neural networks, and support vector regression. We find an enhanced radial basis function artificial neural network outperforms alternate methods used to estimate municipal term structure. This result forms the foundation for establishing a decision theory on optimal municipal bond trading. Using multivariate modeling of a liquidity domain measured across three dependent variables, we investigate the proposed decision theory by estimating weekly production-theoretic bond liquidity returns to scale. Across the three liquidity measures and for almost all weeks investigated, bond trading liquidity is elastic with respect to the modeled factors. This finding leads us to conclude that an optimal trading policy for municipal debt can be implemented on a weekly timescale using the elasticity estimates of bond price, trade size, risk, days-to-maturity, and the macroeconomic influences of labor in the workforce and building activity.

This paper develops a decision evaluation framework to assess how the treatment of risk affects the reliability of, and investment into, electricity generation infrastructure. First, portfolios of electricity generation technologies that comprise the energy supply systems in the US are evaluated using a mean-variance approach. Second, this research assesses the reliability of the portfolios with the aid of loss of load expectation and loss of energy expectation metrics. The methodology considers the least-cost technology mix coupled with the reduction of market and system risks. The variation in the portfolio cost is based on the prevailing policies in the geographic locations. Overall, the current mix of technologies evaluated along the cost-risk latitudes shows an inefficient electricity technology portfolio system. First, investments in renewable technologies may create a bifurcation. On the one hand, the portfolios with significant proportions of the high-cost intermittent technologies exhibit low market risks. On the other hand, these portfolios have less desirable system reliability measures. Second, policy makers will find it instructive that a more diverse electricity technology mix offers the potential to migrate to the efficient frontier in the near term. However, it is imperative to craft policies in support of the transition with the caveat that technology diversity is not always a panacea for improving system reliability even if the portfolio is on the efficient frontier. This work projects some intriguing insights and offers guidance for policy makers.