The Research Department of Economics and Management of Tadbir Nikan Business, Marketing, and Finance Open In Press 2027 03 01 Development of a Decision Support System (DSS) for Supply and Inventory Management: A Case Study of the Cement Industry Development of a Decision Support System (DSS) for Supply and Inventory Management: A Case Study of the Cement Industry 1 18 EN Journal Article 2026 04 01 <p>The objective of this study was to develop a Decision Support System (DSS) for supply and inventory management in the cement industry. The purpose was to provide a mechanism for enhancing decision-making capabilities in addressing supply management and inventory-related problems within the cement industry. This research is classified as an applied study, and accordingly, a field research strategy was adopted. The research methodology is mixed-methods. More specifically, in terms of the logic of data collection, the research approach is inductive-deductive because it examines a phenomenon for which no comprehensive theory exists at the industrial-market level or for which no general consensus has yet been reached. The inductive component involved initially identifying the dimensions and components associated with the characteristics of a Decision Support System (DSS) for supply and inventory management by drawing on previous topics and studies through a literature review. Subsequently, the identified criteria were refined using a critical appraisal method so that substantial theoretical coherence could be achieved through analysis using a hybrid Artificial Neural Network–Genetic Algorithm (ANN-GA) model. In this study, an artificial neural network (ANN), specifically a Multilayer Perceptron Artificial Neural Network (MLP-ANN), was implemented using a backpropagation (BP) learning algorithm. Based on the R² measure, linear regression and MLP regression outperformed the Random Forest algorithm. Although their performance became increasingly similar as the volume of training data increased, scaled MLP regression ultimately outperformed the competing models, achieving a maximum R² value of 0.98. The application of ANN provides an effective means of dealing with nonlinear relationships within datasets or models because of its capabilities in prediction and data fitting. The proposed system can continuously collect and analyze data and assist managers in making better decisions regarding resource procurement and inventory management. Consequently, developing a decision support system based on advanced technologies can steer the cement industry toward greater efficiency, lower costs, and improved production and resource procurement processes. Such innovations can enhance the competitiveness of the cement industry and improve its position in the market.</p> https://www.bmfopen.com/index.php/bmfopen/article/download/565/457