Blockchain-Enabled Governance Mechanisms in Global Supply Networks: A Hybrid Machine Learning and Multiobjective Optimization Framework

Abstract

Abstract It is becoming more difficult for global supply chain networks to be governed because of issues such as a lack of transparency, data fragmentation, regulatory divergence, and the likelihood of having more than one supplier. This paper introduces an innovative Blockchain-Enabled Governance Framework (BEGF) that amalgamates distributed ledger technology with an ensemble machine learning (ML) risk-scoring engine and a multiobjective linear programming (LP) optimizer to enable supply chain decisions that are transparent, real-time, and verifiable. We use the framework in five long-term industrial case studies: automotive (Toyota), pharmaceutical (Merck), electronics (Samsung), apparel (Zara), and food and drink. These studies include 1,840 supplier nodes in 37 countries over 36 months. The BEGF can predict disruptions with an average AUC of 0.947. It can also reduce the number of supply disruptions by 38.5% and save each business $13.8 million a year. The Pareto-optimal optimizer lowers costs all along the supply chain.