EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR SUPPLY CHAIN DISRUPTION PREDICTION IN ENTERPRISE SYSTEMS

Abstract

Supply chain disruptions caused by supplier failures, transportation delays, natural disasters, geopolitical conflicts, and fluctuating customer demand significantly affect enterprise operations and organizational performance. Enterprise Resource Planning (ERP) systems continuously generate operational information related to procurement, production, inventory, logistics, warehouse management, finance, and customer transactions; however, conventional predictive systems often operate as black-box models that provide limited transparency for enterprise decision-makers. Explainable Artificial Intelligence (XAI) addresses this limitation by generating interpretable predictions while providing understandable explanations for disruption risks and recommended mitigation strategies. This paper proposes an Explainable Artificial Intelligence framework for supply chain disruption prediction in enterprise systems by integrating machine learning, ERP analytics, cloud computing, Internet of Things (IoT), business intelligence, and explainable predictive models. The proposed framework continuously analyzes enterprise operational information, predicts potential supply chain disruptions, explains prediction outcomes, and supports intelligent decision-making through transparent analytical reasoning. Experimental evaluation demonstrates improved disruption prediction accuracy, enterprise trust, procurement planning, inventory resilience, logistics coordination, and operational decision-making compared with conventional black-box analytical approaches. Keywords: Explainable Artificial Intelligence, Supply Chain Disruption Prediction, Enterprise Resource Planning, Machine Learning, Predictive Analytics, Business Intelligence, Cloud Computing, Internet of Things, Supply Chain Resilience, Decision Support.