Smart TOPSIS: A Neural Network-Driven TOPSIS with Neutrosophic Triplets for Green Supplier Selection in Sustainable Manufacturing

Abstract

Decision-making in complex environments requires advanced methodologies to manage uncertainty and indeterminacy effectively. This research introduces a novel decision-making framework that integrates the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) with Neutrosophic Triplets (NTs) to address the limitations of decision-making methods in handling indeterminate information. By incorporating a frequency analysis-based ranking strategy and leveraging neural network-driven machine learning, the proposed method significantly enhances the accuracy and computational efficiency of the decision-making process. The necessity of this research stems from the growing complexity of multi-attribute decision-making (MADM) scenarios where traditional methods fall short in accurately ranking alternatives under uncertainty. The novelty lies in integrating NTs with a machine-learning approach, providing a more flexible and robust framework for MADM. The proposed method's contributions are demonstrated through its application in green supplier selection, a critical area in sustainable supply chain management. The results reveal that the smart TOPSIS method improves decision accuracy and reduces computational complexity, making it a viable tool for broader applications. Although the proposed methodology is primarily applied to green supplier selection management, it can also be extended to real-world scenarios in various research fields.