Intelligent Decision Support Machine Learning Based Optimizing Inventory Management

Mona Mohamed¹, Nissreen El Saber ²

¹Higher Technological Institute, 10^th of Ramadan City 44629, Egypt

²Faculty of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt

Emails: mona.fouad@hti.edu.eg; naelsaber@fci.zu.edu.eg

Abstract

Inventory management (InvM) is a critical aspect of supply chain management (SCM) and optimizing inventory levels can lead to significant cost savings and improved customer satisfaction. Hence, business organizations have recently worked to increase the value of their operations by utilizing modern and digital technologies as industry 4.0 (Ind 4.0). In the era of Ind 4.0, the technologies as Internet of Every Things (IoET), AI, BDA…etc. Recognizing the significance of InvM in a supply chain (SC), motivated us to volunteer technologies of Ind 4.0 as machine learning (ML) techniques to boosting Decision Making (DM) process to optimize InvM. Subsequently, this study is constructed for providing an intelligent Decision Support ML framework for automating the process of optimizing inventory management. Our constructed framework ensembles powerful ML prediction algorithms for inventory management, such as Artificial Neural Networks (ANNs), Random Forest (RF), and Support Vector Machine (SVM) for building robust sales regressors.  The extensive experimentations on a case study of Walmart suggested that the proposed system has the potential to transform inventory management and improve supply chain performance, but further research is needed to address the challenges of data availability and quality.

Keywords: Machine Learning; Decision Support Systems; Inventory Management; Inventory Optimization