REAL-TIME SUPPLY CHAIN RISK PREDICTION USING ENTERPRISE RESOURCE PLANNING DATA ANALYTICS

Abstract

Global supply chains are increasingly exposed to operational uncertainties caused by supplier failures, transportation disruptions, fluctuating customer demand, geopolitical events, and changing market conditions. Enterprise Resource Planning (ERP) systems continuously generate valuable operational data across procurement, production, inventory, logistics, finance, and customer management; however, traditional ERP platforms primarily support historical reporting rather than proactive risk prediction. This paper proposes a real-time supply chain risk prediction framework using ERP data analytics by integrating machine learning, cloud computing, Internet of Things (IoT), business intelligence, and predictive analytics. The proposed framework continuously collects enterprise operational information, identifies emerging supply chain risks, predicts disruption probabilities, and provides intelligent recommendations for proactive mitigation strategies. Experimental evaluation demonstrates significant improvements in risk identification accuracy, inventory resilience, supplier monitoring, logistics planning, and enterprise responsiveness compared with conventional ERP-based monitoring systems. The proposed framework enhances organizational resilience by enabling timely and intelligent decisionmaking throughout interconnected supply chain networks. Keywords: Supply Chain Risk Prediction, Enterprise Resource Planning, Predictive Analytics, Machine Learning, Business Intelligence, Cloud Computing, Supply Chain Resilience, Data Analytics, Risk Management, Internet of Things.