PREDICTIVE SUPPLIER PERFORMANCE ASSESSMENT USING INTEGRATED ERP AND OPERATIONAL DATA

Abstract

Supplier performance plays a vital role in ensuring operational continuity, inventory availability, production efficiency, and customer satisfaction across modern supply chain networks. Enterprise Resource Planning (ERP) systems continuously capture procurement transactions, supplier deliveries, inventory records, financial information, production schedules, and logistics activities; however, traditional supplier evaluation approaches primarily rely on historical reports and periodic manual assessments. Such approaches often fail to identify emerging supplier risks before they affect organizational performance. This paper proposes a predictive supplier performance assessment framework using integrated ERP and operational data by combining machine learning, predictive analytics, cloud computing, Internet of Things (IoT), and business intelligence. The proposed framework continuously analyzes supplier delivery performance, procurement efficiency, inventory availability, production dependencies, logistics operations, and financial transactions to predict supplier reliability and generate intelligent procurement recommendations. Experimental analysis demonstrates improved supplier risk prediction, procurement planning, inventory stability, operational resilience, and enterprise decisionmaking compared with conventional ERPbased supplier evaluation systems. Keywords: Supplier Performance Assessment, Enterprise Resource Planning, Predictive Analytics, Machine Learning, Procurement Management, Business Intelligence, Supply Chain Management, Operational Data Analytics, Cloud Computing, Supplier Risk Prediction.