Data Science and Analytics for Decision Support (SIG DSA)
Loading...
Paper Type
ERF
Paper Number
1458
Description
Multi-Criteria Decision-Making (MCDM) methods are widely used in many areas and disciplines. At the same time, they give the strong methodical background of many decision support systems. However, an important and current research issue remains the obtaining reliable results of individual MCDM methods. In this paper, the influence of the used decision matrix normalization method on the obtained rankings is studied on the example of applying the COPRAS method. Five methods are used to normalize matrices of different sizes. The rankings obtained by performing multiple assessments of alternatives are then compared using selected similarity coefficients. The influence of normalization on the final rankings is noticed, which is confirmed by diverse correlations.
Recommended Citation
Kizielewicz, Bartłomiej; Więckowski, Jakub; Shekhovtsov, Andrii; Ziemba, Ewa; Wątróbski, Jarosław; and Sałabun, Wojciech, "Input data preprocessing for the MCDM model: COPRAS method case study" (2021). AMCIS 2021 Proceedings. 11.
https://aisel.aisnet.org/amcis2021/data_science_decision_support/data_science_decision_support/11
Input data preprocessing for the MCDM model: COPRAS method case study
Multi-Criteria Decision-Making (MCDM) methods are widely used in many areas and disciplines. At the same time, they give the strong methodical background of many decision support systems. However, an important and current research issue remains the obtaining reliable results of individual MCDM methods. In this paper, the influence of the used decision matrix normalization method on the obtained rankings is studied on the example of applying the COPRAS method. Five methods are used to normalize matrices of different sizes. The rankings obtained by performing multiple assessments of alternatives are then compared using selected similarity coefficients. The influence of normalization on the final rankings is noticed, which is confirmed by diverse correlations.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.