The increasing complexity and demand for efficiency in business operations have driven organizations to explore automated solutions for their procurement processes. Machine learning (ML), integrated with Enterprise Resource Planning (ERP) systems, is a promising approach for automating procurement workflows, optimizing decision-making, and enhancing operational efficiency. This research explores the use of machine learning algorithms within ERP frameworks to streamline procurement tasks such as supplier selection, demand forecasting, order processing, and inventory management. By leveraging historical data, predictive analytics, and intelligent decision-making systems, organizations can reduce costs, minimize errors, and ensure more accurate procurement outcomes. The study presents a comprehensive approach to automating procurement processes using machine learning within ERP systems. A robust methodology is designed to explore the capabilities of various ML algorithms in predicting procurement needs and enhancing decision-making through datadriven insights. The effectiveness of these techniques is assessed using case studies from industryleading organizations. Furthermore, the research includes an evaluation of the challenges involved in integrating ML with ERP systems, the impact of automation on procurement performance, and the mitigation strategies to overcome these hurdles. Through empirical analysis and comparison with traditional procurement methods, this paper demonstrates the potential benefits of ML-enabled procurement automation, including enhanced accuracy, reduced operational costs, and improved supplier relationship management. By comparing historical data and case study results, the research provides a detailed examination of how machine learning can transform procurement processes in modern organizations.

Machine Learning, ERP Systems, Procurement Automation, Predictive Modeling, Supplier Selection, Inventory Management, Demand Forecasting