Using artificial neural networks and analytic hierarchy process for the supplier selection problem

Pattern classification and its applications are classic domains of study in the area of artificial intelligence. In this study, we integrate neural networks and analytic hierarchy process for the purpose of pattern classification, and showcase the application for the supplier selection problem in the domain of procurement management. Pattern classification has been used for the purpose of supplier base rationalization. In this study, the criteria for decision making have been modeled using fuzzy logic, which further has been modeled as a multi-objective decision making process, by combining the two complementary approaches. The integrated approach drastically reduces the data points required for training and thus extends the applicability of the classifier in the supplier selection domain where the data points is not so high, as is required by classifiers. The proposed integrated approach has been further studied through a case study conducted on a multi-national firm and the results of the analysis have been discussed.