Multicriteria Classification with Unknown Categories: A Clustering–Sorting Approach and an Application to Conflict Management

This work proposes an approach to cluster and sort a set of alternatives considering multi‐criteria categories with a partial order structure. It can be considered a heuristic approach because it does not attempt to derive an optimal partial order among all conceivable clusters of alternatives. Rather than this, it intends to be a simple approach that is transparent to the Decision Maker (DM) whose assistance is sought to help shaping the results. The approach proposed arises from the conjugation of traditional Clustering analysis and Multi‐criteria sorting tools. At the outset, the number of categories and their characteristics is unknown. First, we need to detect only the clusters themselves on the basis of a similarity measure independent of the preferences of the DM. Next, we detect potential partial order relations that might exist between them, according to the subjective preferences of the DM. Such preferences are elicited only after the DM has examined the clusters detected and deemed that these categories made sense. The new approach performs very well in a real‐world problem of management of intragroup conflicts and conflict handling strategies. Copyright © 2012 John Wiley & Sons, Ltd.     

A Comprehensive Decision Approach for Rubber Tree Planting Management in Africa

The main objective of this study is to settle a rigorous field of decision analysis for rubber tree clones selection. Nowadays, there does not exist any process based upon a rigorous method to select the best clone to be plant in order to get the highest return on investment. The only known selection method is to use the experience of different protagonists acting in the plantation. So, we need a tool that takes into account very important criteria in order to achieve the main objective. This goal is achieved by using multicriterion analysis methods to the clone selection. The ranking procedure uses Elimination and Choice Expressing the Reality (ELECTRE III). For each criterion, indifference and preference thresholds are determined after establishing the relative importance of each criterion including rubber tapping, cumulative production during 15 years, cumulative production between 15 and 25 years, wind resistance, disease resistance, physiological resistance, grafting and quality of the rubber. Copyright © 2011 John Wiley & Sons, Ltd.     

A Common Framework for Describing Some Outranking Methods

Outranking methods such as ELECTRE have been proposed for aggregating preference information on several criteria into an overall preference structure in cases where the multiattribute utility approach is not appropriate or feasible. We present here a framework in which such methods may be described and, hopefully in the future, axiomatically characterized. We point out several characteristics such as independence and semiordinality which seem to be pertinent to delineate the field of application of these procedures. © 1997 John Wiley & Sons, Ltd.     

A multicriteria assignment problem

Our objective in this paper is to propose a procedure for solving a multicriteria assignment problem. Given qualitative and quantitative data, the proposed procedure makes assignments taking into consideration the multicriteria aspect of the problem. As an illustrative example, we consider the assignment of referees to the football matches in an Italian championship. Copyright © 2003 John Wiley & Sons, Ltd.     

On computing ELECTRE's credibility indices under partial information

The ELECTRE family of decision aid methods is a well‐known approach to help decision makers (DMs) advance in a decision process. Among the most recent methods in the family, ELECTRE IS, III, and TRI compute fuzzy indices for the credibility of a given action outranking some other. We consider the case when the DMs are unsure which values each parameter should take, which may result from insufficient, imprecise or contradictory information, as well as from different preferences among a group of DMs. In the framework of a robustness analysis approach, where DMs provide only partial information on the parameter values (through constraints on acceptable combinations), we study how to find whether an outranking among two actions in an ELECTRE method is robust. In this context, we study the resulting nonlinear problems of optimizing a credibility index (under the type of constraints that we consider to appear in practice) and present some examples. Copyright © 1999 John Wiley & Sons, Ltd.