A VIKOR and TOPSIS focused reanalysis of the MADM methods based on logarithmic normalization

TL;DR

This paper reanalyzes the MADM methods VIKOR and TOPSIS using a novel logarithmic normalization technique, comparing results with classical methods and assessing the impact on decision-making outcomes.

Contribution

Introduces the application of logarithmic normalization to MADM methods VIKOR and TOPSIS, highlighting differences and reliability in decision analysis.

Findings

Logarithmic normalization affects MADM results.

Differences observed between classical and LN-based methods.

Sensitivity analysis confirms result reliability.

Abstract

Decision and policy-makers in multi-criteria decision-making analysis take into account some strategies in order to analyze outcomes and to finally make an effective and more precise decision. Among those strategies, the modification of the normalization process in the multiple-criteria decision-making algorithm is still a question due to the confrontation of many normalization tools. Normalization is the basic action in defining and solving a MADM problem and a MADM model. Normalization is the first, also necessary, step in solving, i.e. the application of a MADM method. It is a fact that the selection of normalization methods has a direct effect on the results. One of the latest normalization methods introduced is the Logarithmic Normalization (LN) method. This new method has a distinguished advantage, reflecting in that a sum of the normalized values of criteria always equals 1. This normalization method had never been applied in any MADM methods before. This research study is focused on the analysis of the classical MADM methods based on logarithmic normalization. VIKOR and TOPSIS, as the two famous MADM methods, were selected for this reanalysis research study. Two numerical examples were checked in both methods, based on both the classical and the novel ways based on the LN. The results indicate that there are differences between the two approaches. Eventually, a sensitivity analysis is also designed to illustrate the reliability of the final results.