"Formal decision and evaluation models are sets of explicit and well-defined rules to collect, assess, and process information in order to be able to make recommendations in decision and/or ...evaluation processes. They are so widespread that almost no one can pretend not to have used or suffered the consequences of one of them. Our earlier companion volume, Evaluation and Decision Models, heavily criticised formal models but also argued that they could be useful. On the other hand, Evaluation and Decision Models with Multiple Criteria is a guide aimed at helping the analyst to choose a model and use it consistently. We propose a sound analysis of techniques and our presentation can be extended to most decision and evaluation models as a ""decision aiding methodology"". This volume is intended for the enlightened practitioner, for anyone who uses decision or evaluation models---for research or for applications---and is willing to question his practice, to have a deeper understanding of what he does."
The theory of Vector Optimization is developed by a systematic usage of infimum and supremum. In order to get existence and appropriate properties of the infimum, the image space of the vector ...optimization problem is embedded into a larger space, which is a subset of the power set, in fact, the space of self-infimal sets. Based on this idea we establish solution concepts, existence and duality results and algorithms for the linear case. The main advantage of this approach is the high degree of analogy to corresponding results of Scalar Optimization. The concepts and results are used to explain and to improve practically relevant algorithms for linear vector optimization problems.
Recent advances in Natural Language Processing and Machine Learning provide us with the tools to build predictive models that can be used to unveil patterns driving judicial decisions. This can be ...useful, for both lawyers and judges, as an assisting tool to rapidly identify cases and extract patterns which lead to certain decisions. This paper presents the first systematic study on predicting the outcome of cases tried by the European Court of Human Rights based solely on textual content. We formulate a binary classification task where the input of our classifiers is the textual content extracted from a case and the target output is the actual judgment as to whether there has been a violation of an article of the convention of human rights. Textual information is represented using contiguous word sequences, i.e., N-grams, and topics. Our models can predict the court’s decisions with a strong accuracy (79% on average). Our empirical analysis indicates that the formal facts of a case are the most important predictive factor. This is consistent with the theory of legal realism suggesting that judicial decision-making is significantly affected by the stimulus of the facts. We also observe that the topical content of a case is another important feature in this classification task and explore this relationship further by conducting a qualitative analysis.
Sepsis is the third leading cause of death worldwide and the main cause of mortality in hospitals
, but the best treatment strategy remains uncertain. In particular, evidence suggests that current ...practices in the administration of intravenous fluids and vasopressors are suboptimal and likely induce harm in a proportion of patients
. To tackle this sequential decision-making problem, we developed a reinforcement learning agent, the Artificial Intelligence (AI) Clinician, which extracted implicit knowledge from an amount of patient data that exceeds by many-fold the life-time experience of human clinicians and learned optimal treatment by analyzing a myriad of (mostly suboptimal) treatment decisions. We demonstrate that the value of the AI Clinician's selected treatment is on average reliably higher than human clinicians. In a large validation cohort independent of the training data, mortality was lowest in patients for whom clinicians' actual doses matched the AI decisions. Our model provides individualized and clinically interpretable treatment decisions for sepsis that could improve patient outcomes.
Decision-theoretic rough set provides a new perspective to handle decision-making problems under uncertainty and risk. The three-way decision theory proposed by Yao is based on rough set theory and ...is a natural extension of the classical two-way decision approach. In this paper, we introduce the idea of decision-theoretic rough set into multigranulation approximation space and explore the rough approximation of a fuzzy decision object under the framework of two universes. We construct a variable precision multigranulation fuzzy decision-theoretic rough set over two universes by using the concept of an arbitrary binary fuzzy relation class between two different universes and the probability measurement of a fuzzy event. Several interesting properties of the proposed model are addressed and the decision rules are also deduced using the concept of three-way decision-making over two universes. Moreover, two special types of optimistic and pessimistic models are given by using different precision parameters. We then present a new approach to multiple criteria group decision making problems, based on variable precision multigranulation fuzzy decision-theoretic rough set over two universes. Meanwhile, we establish a cost-based method for sorting among all alternatives of group decision-making problems. Finally, an example of handling a medical diagnosis problem illustrates this approach.
•A new multigranulation fuzzy decision-theoretic rough set over two universes was defined.•The relationship between the proposed model with the existing decision-theoretic rough set models was established.•The three-way decision was deduced based on the multigranulation fuzzy decision-theoretic rough set over two universes.•Multigranulation fuzzy decision-theoretic rough set-based three-way group decision making method was established over two universes.
This book presents adaptive solution methods for multiobjective optimization problems based on parameter dependent scalarization approaches. With the help of sensitivity results an adaptive parameter ...control is developed such that high-quality approximations of the efficient set are generated. These examinations are based on a special scalarization approach, but the application of these results to many other well-known scalarization methods is also presented. Thereby very general multiobjective optimization problems are considered with an arbitrary partial ordering defined by a closed pointed convex cone in the objective space. The effectiveness of these new methods is demonstrated with several test problems as well as with a recent problem in intensity-modulated radiotherapy. The book concludes with a further application: a procedure for solving multiobjective bilevel optimization problems is given and is applied to a bicriteria bilevel problem in medical engineering.
Three-way group decisions provide an efficient method to settle complex and high risk decision-making problems. To obtain reasonable decision results that satisfy different backgrounds and knowledge ...of decision makers, it is necessary to design a proper consensus reaching process (CRP) for loss functions of decision-theoretic rough sets (DTRSs). Unlike existing researches, this paper not only extends the group relationship among decision makers to the social network, but also considers the externality of social trust network in group decision making. In light of this idea, we design a new CRP with the externality of social network for three-way group decisions. In the CRP, the adjustment of a decision maker who is persuaded by the moderator can influence other decision makers to accordingly adjust evaluations. Thus, by using the linkage externality influence among decision makers, we establish a two-stage mixed 0–1 linear optimization consensus model for the determination of loss functions of DTRSs. Then, based on Bayesian decision procedure, we construct a complete decision procedure for three-way group decisions with social network. Finally, we apply our proposed method to assess desert locust invasion areas and verify its validity.
In management, decisions are expected to be based on rational analytics rather than intuition. But intuition, as a human evolutionary achievement, offers wisdom that, despite all the advances in ...rational analytics and AI, should be used constructively when recruiting and winning personnel. Integrating these inner experiential competencies with rational-analytical procedures leads to smart recruiting decisions.
The last 25 years have witnessed growing recognition that natural resource management decisions depend as much on understanding humans and their social interactions as on understanding the ...interactions between non-human organisms and their environment. Decision science provides a framework for integrating ecological and social factors into a decision, but challenges to integration remain. The decision-analytic framework elicits values and preferences to help articulate objectives, and then evaluates the outcomes of alternative management actions to achieve these objectives. Integrating social science into these steps can be hindered by failing to include social scientists as more than stakeholder-process facilitators, assuming that specific decision-analytic skills are commonplace for social scientists, misperceptions of social data as inherently qualitative, timescale mismatches for iterating through decision analysis and collecting relevant social data, difficulties in predicting human behavior, and failures of institutions to recognize the importance of this integration. We engage these challenges, and suggest solutions to them, helping move forward the integration of social and biological/ecological knowledge and considerations in decision-making.