Clustering Student Satisfaction Levels Regarding the Free Nutritious Food Program at SMAN 1 Delitua Using the K-Means Algorithm

Abstract

The Free Nutritious Food (MBG) Program is a strategic policy initiated by the Indonesian government to improve the nutritional status and academic performance of students. This study aims to cluster the satisfaction levels of students at SMAN 1 Delitua regarding the MBG Program using a data mining approach with the K-Means clustering algorithm. A quantitative approach was employed, utilizing a Likert-scale questionnaire (1–5) to evaluate eight satisfaction indicators: taste, quality, menu variation, portion, cleanliness, timeliness, health benefits, and overall satisfaction. The study population comprised all students at SMAN 1 Delitua, with a sample of 600 respondents (350 males and 250 females) selected via stratified random sampling. The optimal number of clusters was determined using the Elbow Method and the Silhouette Score. The K-Means algorithm identified five distinct clusters representing varying satisfaction levels: very low (6.33%), low (13.00%), moderate (62.67%), high (11.17%), and very high (6.83%). The predominance of moderate to high satisfaction levels indicates that the MBG Program is generally well-received by the students. This research contributes a data-driven evaluation model for school nutrition policies and offers targeted recommendations for improving satisfaction among underperforming segments.