Exploring TOPSIS based algorithm for non-homogeneous alternatives in group decision making

Abstract

The purpose of this work is to explore an algorithm based on Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for non-homogeneous alternatives in group decision making. In this particular case of evaluating a set of decision alternatives, an individual expert expresses hedonic judgments for a subset of decision alternatives depending on his/her knowledge about the alternatives. The structure of the decision making problem generates a local matrix of judgmental responses for each decision alternative. Signal-to-Noise Ratio (SNR) determines the ratio of relevant information to irrelevant information in the local response matrices. The SNR vectors of all decision alternatives are aggregated into a global decision matrix and passed as argument to the TOPSIS algorithm to rank the alternatives. The attractiveness of this algorithm is that we do not have to modify the existing TOPSIS. The algorithm was used to rank 10 different sports that were evaluated by 34 respondents in a survey and the result is practically appealing. This type of non-homogeneous group decision making is particularly useful in selecting an optimal decision alternative among a large set of alternatives where opinions of a large group of stakeholders count. This is for instance in opinion polls, comparison of market products/services and Delphi process where an expert does not necessarily have to possess full knowledge about all decision alternatives or be jack of all trades.