Impact of Machine Learning on Applying the Best Worst Method for Social Sustainability in Manufacturing Supply Chains

This research is carried out merging ML with BWM to intensify decision making in manufacturing supply chain using social sustainability under light. As companies become more focused on environmental sustainability, the capability of machine learning to effectively assess and prioritize sustainability criteria should be highly valued. Through a team of domain experts, the research clearly identifies the most vital social sustainability factors and, afterwards, deploys ML algorithms to analyze and optimize the provided decision-making framework by BWM. The selected approach gives possibility to dynamic weighting of the criteria which is based on real-time data. This way we are able to come up with the more precise and effective sustainability strategies. The results show that the hybrid ML-BWM model is not only an effective tool to enhance the validity and accuracy of evaluations but also one that provides the prudent directions that help the manufacturing sector shape its choice and responses. This paper analyzes the possible outcome of the integration of AI and traditional approach to decision-making process on social aspects of sustainability within supply chain.