Application of fuzzy TRUST CRADIS method for selection of sustainable suppliers in agribusiness

Puška, Adis and Nedeljković, Miroslav and Stojanović, Ilija and Božanić, Darko (2023) Application of fuzzy TRUST CRADIS method for selection of sustainable suppliers in agribusiness. Sustainability, 15 (3). ISSN 2071-1050

Text Puška, Nedeljković, Stojanović, Božanić - Sustainability.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (793kB)

Abstract

This study deals with the selection of a sustainable supplier on the example of the agribusiness company Mamex from Bosnia and Herzegovina. The main problem of this research is the selection of a sustainable supplier as a part of the sustainable strategy of the Mamex company. One of the prerequisites is that suppliers must present sustainability principles in business by having an appropriate certificate. The results of the selection of sustainable suppliers are completed using a new hybrid fuzzy approach with the methods IMF SWARA (Improved Fuzzy Stepwise Weight Assessment Ratio Analysis) and fuzzy TRUST (multi-normalization multi-distance assessment) CRADIS (compromise ranking of alternatives from distance to ideal solution) methods. The innovative approach is reflected in the use of a combination of these methods, especially by combining the TRUST and CRADIS methods into one method. The IMF SWARA method shows that the most important main criterion is the economic criterion, while the least important is the social criterion. By applying the fuzzy TRUST CRADIS method, it is found that out of the observed six suppliers, the second supplier has the best indicators. These results are confirmed by other fuzzy methods: MABAC (multi-attributive border approximation area comparison), WASPAS (weighted aggregated sum product assessment), fuzzy SAW (simple additive weighting), MARCOS (measurement of alternatives and ranking according to compromise solution), ARAS (a new additive ratio assessment), and TOPSIS (technique for order preference by similarity to an ideal solution). This research shows that applying more normalization when ranking alternatives reduces the influence of individual normalizations, and this approach should be used in future research.

Actions (login required)

View Item