ADAPTIVE PRODUCTION PLANNING THROUGH MACHINE LEARNING AND ERP-CONNECTED SUPPLY CHAIN DATA

Abstract

Adaptive production planning has become essential for manufacturing organizations operating in highly dynamic supply chain environments characterized by fluctuating customer demand, supplier uncertainties, inventory variability, and changing market conditions. Enterprise Resource Planning (ERP) systems integrate procurement, production scheduling, inventory management, warehouse operations, logistics, finance, and customer relationship management into centralized enterprise platforms; however, conventional ERP systems primarily support historical planning rather than adaptive predictive decision-making. Machine learning enables organizations to continuously analyze enterprise operational information, forecast production requirements, optimize resource allocation, and dynamically adjust production schedules in response to real-time operational changes. This paper proposes an adaptive production planning framework using machine learning and ERP-connected supply chain data by integrating predictive analytics, cloud computing, Internet of Things (IoT), business intelligence, and enterprise resource optimization. The proposed framework continuously evaluates procurement activities, supplier performance, inventory availability, production capacity, logistics coordination, and customer demand to generate intelligent production planning recommendations. Experimental analysis demonstrates significant improvements in production efficiency, scheduling accuracy, inventory optimization, operational flexibility, and enterprise decisionmaking compared with conventional ERPsupported production planning systems. Keywords: Adaptive Production Planning, Enterprise Resource Planning, Machine Learning, Predictive Analytics, Supply Chain Management, Manufacturing Systems, Business Intelligence, Cloud Computing, Internet of Things, Production Optimization.