<![CDATA[This study addresses the issue of inaccurate production forecasting among breakfast-serving SMEs in Medan due to fluctuations in demand, which often result in food waste and financial losses. The objective of this study is to develop a classification model for daily consumption levels (high, medium, low) to serve as the basis for production recommendations. The method used is the C4.5 Decision Tree algorithm with a dataset of 92 daily operational records covering the attributes of production catesgory, menu type, weather conditions, and operational days. The data was preprocessed through attribute categorization, then analyzed using entropy and gain ratio calculations to form a decision tree. Model evaluation was performed using 10-fold cross-validation in RapidMiner. The results showed that the production category attribute had the highest gain ratio, making it the root of the decision tree. The resulting model achieved an accuracy of 57.56% with a deviation of ±7.85%, performing best in the moderate consumption class. The primary contribution of this study is the generation of IF–THEN-based decision rules that can be practically applied by SMEs to adjust daily production volumes based on operational conditions, thereby helping to reduce potential food waste without requiring complex calculations.]]>
Copyrights © 2026
