Development of a Decision Support System for Perishable Food Management in Culinary Education Institutions Using Machine Learning with Linear Regression

Abstract

This study presents the development of a decision support system tailored for educational institutions with culinary programs, aimed at optimizing the management of perishable food items. The system employs a machine learning approach, specifically linear regression, to predict and enhance decision-making regarding the handling, storage, and utilization of perishable ingredients. The foundation of the system lies in the collection and analysis of historical data pertaining to various perishable food items commonly utilized in culinary education. Key variables, including temperature, humidity, storage duration, and other relevant factors, are identified to build a robust linear regression model. This model serves to predict the remaining shelf life of perishable goods, offering valuable insights into optimal storage conditions. Instructors benefit from a tool that enhances the practical learning experience, fostering a deeper understanding of food preservation and waste reduction. Continuous feedback mechanisms are integrated to improve the system's accuracy and relevance over time. Culinary educators can contribute insights, ensuring that the system remains aligned with the dynamic needs of culinary education.By incorporating this decision support system into culinary programs, educational institutions can not only empower students with practical skills but also in still a culture of sustainability and resource efficiency. The linear regression model, as a part of the system, aids in making informed decisions that align with industry best practices, contributing to the development of responsible and skilled culinary professionals. This research represents a significant step towards leveraging machine learning techniques to enhance culinary education, offering a practical and innovative solution for the management of perishable food items within educational settings.