A New Approach to Assessing the Biases of Decisions based on Multiple Attribute Decision making Methods

Abstract

The emerging more sophisticated computer hardware and software provide the users in various areas of activities with ample opportunity to use various computer-aided systems. One type of these systems includes decision support systems based on the use of multiple attribute decision making methods. In designing such systems, the question arises, which of MADM methods is more efficient and should be used in evaluating taking into account that the best alternatives yielded by these methods often differ. A great number of researchers are trying to answer these and other similar questions. However, they usually arrive at the same conclusion that the considered methods are based on different principles, but the best (or most efficient) MADM method can hardly be found. Therefore, the authors of the present paper offer a method of evaluating the reliability of decisions, obtained by using MADM methods and their biases, taking into account the biases of the initial data pertaining to the problem solved and basic principles of various multiple attribute decision making methods applied. Ill. 1, bibl. 12, tabl. 2 (in English; abstracts in English and Lithuanian).

DOI: http://dx.doi.org/10.5755/j01.eee.117.1.1048