AI-DRIVEN INVENTORY OPTIMIZATION FOR MULTI-TIER ERPCONNECTED SUPPLY CHAIN SYSTEMS

Abstract

Inventory optimization has become one of the most critical challenges in modern multi-tier supply chain systems due to fluctuating customer demand, supplier uncertainties, transportation delays, and increasing operational complexity. Enterprise Resource Planning (ERP) systems integrate procurement, warehouse management, production planning, inventory control, finance, and logistics into a unified enterprise platform; however, conventional ERP systems primarily support transaction processing rather than intelligent inventory optimization. Artificial Intelligence (AI) enables organizations to continuously analyze enterprise operational data, predict inventory requirements, optimize stock allocation, and proactively mitigate supply chain disruptions. This paper proposes an AIdriven inventory optimization framework for multi-tier ERP-connected supply chain systems by integrating machine learning, predictive analytics, cloud computing, Internet of Things (IoT), and business intelligence. The proposed framework continuously evaluates inventory movement, supplier performance, production schedules, warehouse utilization, logistics operations, and customer demand to generate intelligent inventory recommendations. Experimental analysis demonstrates improved inventory utilization, reduced stock shortages, optimized warehouse operations, enhanced procurement planning, and increased supply chain resilience compared with conventional ERP inventory management systems. Keywords: Artificial Intelligence, Inventory Optimization, Enterprise Resource Planning, Supply Chain Management, Machine Learning, Predictive Analytics, Multi-Tier Supply Chain, Cloud Computing, Warehouse Management, Business Intelligence.