<![CDATA[Inventory management is a critical component of supply chain operations, particularly for culinary Micro, Small, and Medium Enterprises (MSMEs) that face volatile demand patterns and perishable raw materials. Inaccurate procurement decisions may result in overstocking, stock shortages, and financial losses. Although artificial intelligence approaches such as machine learning have been widely applied in inventory forecasting, these methods typically require large-scale historical datasets and advanced computational infrastructure, which are often unavailable in MSME environments. This study proposes an explainable hierarchical rule-based inference model designed to support inventory optimization in data-scarce culinary MSMEs. The model integrates dynamic operational factors, including day type, weather conditions, supplier lead time, and special events, into a transparent decision-making mechanism based on IF–THEN rules. The research adopts a Research and Development methodology using the Waterfall framework, covering requirement analysis, rule-base construction, system implementation, and evaluation. Model validation was conducted through 20 expert-verified decision scenarios and assessed using confusion matrix metrics. The experimental results demonstrate that the proposed system achieved 90% accuracy, 92.3% precision, 92.3% recall, and a 92.3% F1-score when compared with expert procurement decisions. These findings indicate that explainable rule-based systems remain a practical and reliable solution for inventory decision support in culinary MSMEs with limited data resources.]]>
Copyrights © 2026
