AUTOMATION OF SUPPLIER SELECTION IN SUPPLY CHAINS BASED ON MULTI-CRITERIA NEURAL NETWORK MODELS

Abstract

The article substantiates the relevance of using multi-criteria neural models in supplier selection in supply chains. Modern approaches of Ukrainian and foreign scientists to supplier evaluation and selection criteria are considered, in particular, methods of multi-criteria analysis and artificial neural networks. The essence and types of multi-criteria analysis, advantages and key features of multi-criteria neural models are determined. The stages of the process of working with a multi-criteria neural model in the process of supplier selection in supply chains are determined. The stages of implementation, advantages and disadvantages of the Analytic Hierarchy Process, TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) and ELECTRE (Elimination et Choix Traduisant la Realité) methods in the process of multi-criteria supplier selection are summarized. Theoretical and applied aspects of automation of supplier selection in supply chains based on multi-criteria neural models are investigated. The feasibility of using multi-criteria neural models to increase the efficiency of managerial decision-making is substantiated. The benefits of automating supplier selection in supply chains are substantiated. An approach to integrating artificial neural networks with multi-criteria analysis methods is proposed. Key criteria for evaluating suppliers are identified and a model for their optimal selection is formed. The proposed integrated approach allows taking into account the complex structure of relationships between evaluation criteria and provides a more informed selection of suppliers. The results obtained indicate that the use of multi-criteria models allows for a more informed selection of suppliers, and the integration of neural networks increases the accuracy of the assessment by taking into account complex relationships between criteria. The study found that automating supplier selection using multi-criteria neural network models is an effective tool for improving the efficiency of a company’s procurement logistics and supply chain management as a whole.