International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/1912 2020 2020 Decision Support Department, Faculty of Computers and Informatics Zagazig University, Zagazig, 44519, Egypt Esraa Kamal Decision Support Department, Faculty of Computers and Informatics Zagazig University, Zagazig, 44519, Egypt Amal F. Abdel Abdel-Gawad Decision Support Department, Faculty of Computers and Informatics Zagazig University, Zagazig, 44519, Egypt Shereen Zaki Supply Chain Management (SCM) plays a critical role in the success of any business organization. Individuals involved in business activities often have to make decisions regarding different aspects of the supply chain, including planning, procurement, production, inventory management, transportation, distribution, and customer relationship management. The combination of neutrosophic logic and machine learning has gained significant attention in the field of SCM as a means to tackle uncertainties and improve decision-making. This paper highlights the potential benefits and applications of integrating neutrosophic reasoning and machine learning in SCM. Neutrosophic reasoning provides a framework for handling imprecise and uncertain information, while machine learning techniques offer powerful tools for data analysis, pattern recognition, and predictive modeling. By leveraging machine learning algorithms within the context of neutrosophic logic, SCM practitioners can enhance demand forecasting accuracy, optimize inventory management, improve transportation and routing decisions, and strengthen supply chain collaboration. The integration of neutrosophic logic and machine learning enables the handling of complex supply chain data, accommodates dynamic and uncertain environments, and supports proactive decision-making. Furthermore, the combination of these approaches can contribute to improved supply chain resilience, sustainability, and customer satisfaction. This paper applied the neutrosophic AHP method as a feature section to select the highest importance criteria as an input to machine learning. Then we applied two machine learning models named random forest and decision. The results show the random forest has the highest accuracy followed by a decision tree. 2023 2023 142 160 10.54216/IJNS.210213 https://www.americaspg.com/articleinfo/21/show/1912