Determined by Tolerances with Rough Set Based MCDM

Abstract

Problem definition: Rough set based MCDM method has been developed for rule extraction and classification from inconsistent and incomplete data structures. During the analysis, lower and upper approaches use the incomplete and uncertain data. Incomplete information analysis and knowledge base reduction methods can able to use the minimization of uncertainty also the structure does not contain strict constraints like fuzzy sets. Academic / Practical relevance: The rough set, first proposed by Pawlak [1] in 1982, that enables the discovery of the necessary information using large databases, as well as it can be used in the analysis of missing data structures and uncertain data. Also developed algorithm can be used as a tool in multi-criteria decision making techniques. Methodology: The rough set concept was developed to analyze of imprecise structures in multi-criteria decision making problems, and it was derived from fuzzy logic approach by evaluating the data which covers the lower and upper limits. Results: The results were solved with the developed algorithm, entropy-based approach, fuzzy MCDM, fuzzy AHP, and compared with the rough set-based approach that gave the same results with the fuzzy logic based MCDM, fuzzy logic based AHP, while the entropy-based result gave 75% similar results. It shows that the proposed method is reliable and suitable as other MCDM methods. Managerial implications: In view of the fact that the data are uncertain or incomplete, the existing multi-criteria decision making methods will be insufficient, seeing as the rough set-based multi-criteria decision making algorithm can able to overcome this deficiency.