<![CDATA[Parental satisfaction in learning methods is an important indicator for evaluating the quality of education, especially in inclusive schools such as Smart Aurica School. This study aims to predict the level of parental satisfaction with learning methods using the K-Nearest Neighbor (K-NN) algorithm. The research employed a quantitative approach with data collected through questionnaires distributed to parents of students. The collected data were processed through several stages, including data cleaning, normalization, training and testing set division, and distance calculation using Euclidean Distance. The K-NN model was then applied to classify satisfaction levels based on the predetermined K value. The results indicate that the K-NN algorithm can provide accurate predictions of parental satisfaction, achieving a relatively high accuracy rate in testing. These findings demonstrate that K-NN is an effective approach to assist schools in evaluating learning methods and offering data-driven recommendations to improve educational quality. Therefore, this research contributes to the application of machine learning in providing a more objective and accurate evaluation of educational services, which can serve as a strategic basis for school decision-making.]]>
Copyrights © 2025
