Application of an MCDM model with data mining techniques for green supplier evaluation and selection

Abstract

The evaluation and selection of green suppliers are some of the most important tasks in green supply chain management (GSCM). The purpose of this study is to develop an effective green supplier evaluation model. Currently the evaluation criteria are determined through a literature review combined with decision-maker opinions. A few studies have used data mining techniques to screen the core criteria. This study proposes a novel hybrid MCDM model, that integrates the support vector machine (SVM), the fuzzy best worst method (FBWM) and, the fuzzy technique for order preference by similarity to an ideal solution (FTOPSIS) approaches to select the most suitable green suppliers. A case study, using data from a multinational electronics manufacturer, is carried out for illustration. First, the SVM is used to extract the core criteria from the historical data. The original 25 criteria are reduced to 13 criteria. Then, the FBWM is used to obtain the weights of the core criteria. Finally, the FTOPSIS is used to integrate the performance and prioritize the green suppliers. Finally, practical management implications and suggestions for improvement for decision-makers and green suppliers are provided