International Journal of Multicriteria Decision Making (3 papers in press)

Regular Issues

• Strengthening Preference Ranking Organisation MeTHod for Enrichment Evaluation with Features of Paraconsistent Pavelka Style Fuzzy Logic  
  by Inusah Abdulai 
  Abstract: In this study, a new technique of complete ranking is proposed to augment the efficiency of the Preference Ranking Organisation MeTHod for Enrichment Evaluation (PROMETHEE) methodology. The technique employs some ideas of the PROMETHEE method, and paraconsistent Pavelka style fuzzy logic. To illustrate the effectiveness and efficiency of this novel technique, data on the performance of five mobile phone operators in Ghana is analysed and the results compared with the ranking of the conventional PROMETHEE I and II.
  Keywords: Paraconsistent logic; Pavelka logic; Leaving and entering flows; Evidence couple; Evidence matrices; PROMETHEE; Paraconsistent Pavelka style fuzzy logic; MV-algebra; Complete ranking.
  
  
• Multiplicative aggregation in managerial multi-attribute decision making  
  by Maksim Goman, Stefan Koch 
  Abstract: Purpose -- This paper focuses on measuring the performance of alternatives for management decision making. A multiplicative approach is suggested for aggregation of criteria estimates assuming that the criteria are measured in non-comparable units of measure. We extensively compare weighted average (WA) and newly proposed composite index (CI) in a real-world example of strategic decision making problem of enterprise resource planning (ERP) system upgrade. In addition, user preference on decision support method complexity was examined. Design -- The method uses a CI based on weighted product (WP) instead of commonly applied WA. We develop the CI, illustrate its application and performance with an ERP upgrade decision making problem. A survey of potential users was performed to evaluate comprehension of the CI method in the context of the current WA practice and availability of other decision support methods, and willingness to use it as compared with WA and a number of other formal decision support methods. Findings -- Application of the proposed CI method to the decision problem of ERP system upgrade shows its robustness to data scale change. Empirical evaluation of user acceptance revealed that users are more likely to understand simple methods and apply them in practical work rather than methods that they do not comprehend, with the proposed approach rated "statistically not worse" than simple WA, thus making the new approach a viable alternative for managers. Originality/Value -- The findings of this paper should help managers in practical multi-attribute problems where ranking of alternatives based on a number of their properties having non-comparable values is required. The overall value of each alternative is obtained in mathematically correct way, and the aggregation of the overall value is simplified due to absence of necessary data normalization. At the same time, application of the method in management decision making is as simple as traditional WA. And because ease of understanding and use is important for users, multiplicative aggregation technique deserves much attention in practical applications.
  Keywords: multiple criteria analysis; weighted product; weighted average; multi-attribute decision making; strategic decision making; software selection.
  
  

Special Issue on: Composite Indicators and Multicriteria Decision Making New Developments and Applications

• A Non-linear Multivariate Method for Constructing Profiles of Country Performance  
  by Sara Casacci, Adriano Pareto 
  Abstract: Composite indices for measuring multi-dimensional phenomena such as sustainable development, quality of life, and competitiveness, are based on individual indicators that have no common unit of measurement. As a rule, individual indicators are normalized by univariate methods, independently of each other. However, normalization has a strong impact on results since it creates a correspondence system among different variables. Thus the normalization method should take into account the relationships existing in the data. In this paper, a non-linear multivariate method is proposed for normalizing a set of individual indicators in order to aggregate them into a composite index and construct profiles of country performance. An application to the measurement and analysis of socio-economic development is also shown.
  Keywords: composite index; indicators; normalization; non-linear relationship.