A Novel Approach to Social Sustainability with Machine Learning and the Best Worst Method in Manufacturing

This paper is aimed at presenting a novel approach for enhancing the measurement of social sustainability in manufacturing domain with the help of ML with BWM. Social sustainability when dealing with manufacturing is part of the four sustainability pillars that seeks to address aspects such as; welfare of workers, social organization, and practice within the firm. This is why the conventional tools may not sufficiently inform on the right combination of the said aspects. The information from the big data is then processed by the means of ML to disclose the patterns illuminating the stance influences and BWM is integrated to analyze specialists’ insight the power of evolving influential aspects of stance. They are useful in minimizing the time as well as the energy required in the formulation of the decisions because the details and correlations needed are already provided. It is illustrated with the help of an example in the manufacturing setting and significant improvements in the values of the social sustainability indices compared to the classical approach. From these conclusions, it is possible to indicate the prospects for the integration of ML and BWM as the authors’ contribution to tackling the problem of social sustainability in the manufacturing sector.