<![CDATA[Raw material inventory management is a critical factor in the food industry, influencing production efficiency and product quality. Unstable inventory levels can lead to significant challenges, including material spoilage, stock shortages, and quality degradation, ultimately impacting the ability to meet market demand. To address the complexities and uncertainties inherent in inventory management, this study explores the application of Fuzzy Sugeno inference systems. This method allows for the flexible processing of imprecise inventory data, generating accurate numerical outputs that can directly inform operational decision-making. By analyzing production data for pie crusts from April 2023 to May 2024, the study identified significant fluctuations in initial stock, production, and incoming stock levels. To capture the inherent uncertainty in these parameters, Fuzzy Sugeno was employed to categorize them into fuzzy sets. The implementation of the model in MATLAB yielded precise outputs that align with the specific needs of inventory management in the food industry. The results demonstrate that the proposed Fuzzy Sugeno-based approach can significantly enhance inventory prediction accuracy and reduce the risk of stockouts or excess inventory. By adapting to changing market demands and operational conditions, this method contributes to improved production efficiency, cost reduction, and overall business sustainability in the food industry.]]>
Copyrights © 2025
