A hybrid group decision support system for supplier selection using analytic hierarchy process, fuzzy set theory and neural network

• Group decision support models for supplier selection have been proposed.
• The models integrate analytic hierarchy process, neural network and fuzzy sets.
• Fuzzy AHP for group decision making was used to estimate group preferences.
• Neural networks were used to map suppliers to suitable classes.
• Performance of proposed hybrid method tested through a case study.

Within procurement literature; many studies focus on providing decision support to the supplier selection problem. However, studies on group decision support are yet to be explored extensively within supplier selection literature, despite its benefits. This study presents the application of a hybrid approach for group decision support for the supplier selection problem. fuzzy set theory, analytic hierarchy process and neural networks have been integrated to provide group decision support under consensus achievement. Discriminant analysis has been used for the purpose of supplier base rationalization, through which suppliers have been mapped to highly suitable and less suitable supplier classes. The proposed integrated approach has been further studied through two case studies and the proposed approach has been compared with another approach for group decision making under consensus and other approaches for prioritization using AHP, without consensus achievement. A very high accuracy in capturing the collective consensual preferences of the group was established across eight cross-validation tests from the two case studies, for the hybrid approach, even with extremely limited count of data sets which were used for training the hybrid model.