An integrated MCDM-ML approach for predicting the carbon neutrality index in manufacturing supply chains

Organizations across the globe are devising novel approaches to strive for carbon neutrality. Global institutions have manifested the critical need to develop reasonable strategies in every sector to mitigate the impending issues of excessive anthropogenic carbon emission and, in consequence, climate change. World-leading economies have initiated significant steps by developing zero-carbon emission policies to monitor the escalating carbon emissions to curb global warming. The clothing industry has a substantial carbon footprint while causing environmental pollution. Based on transition management theory, this study aims to explore and evaluate the critical determinants that can assist in pursuing carbon neutrality in the clothing industry. A decision support system comprising an integrated voting analytical hierarchy process (VAHP) and Bayesian network (BN) method fulfills our purpose. Pertinent literature is reviewed to determine the critical determinants for carbon neutrality (CDs-CN). After that, the VAHP method is employed to prioritize the CDs-CN. Further, the influence of CDs-CN on achieving carbon neutrality is modeled using a BN, predicting the carbon neutrality index (CNI) for the clothing industry. The findings reveal that professional expertise, laws and certifications, technological acceptance, availability of decarbonizing methods, and adequate carbon offsetting are the essential CDs-CN. This research extends the existing knowledge on integrating MCDM-ML techniques to address predictive modelling-based problems involving complex structures. Simultaneously, the present study helps practitioners and policymakers understand the key CDs-CN to successfully build and manage a carbon-neutral clothing industry by adopting the suggested strategies. Finally, recommendations concerning sustainable development goals (SDGs) are provided to achieve carbon-neutral manufacturing supply chains.