Analysis of Student Excellence Classes in Data Mining Using the KNN Method

Abstract

Excellent classes are programs designed to maximize the academic and non-academic potential of students and girls, with the aim of improving their overall achievement. This program aims to provide more intensive learning and a curriculum tailored to students' needs and abilities, so that they can develop their talents and competencies optimally. In order to evaluate the effectiveness of the superior class program and to identify students who are most suitable for the program, this research was conducted using the K-Nearest Neighbors (KNN) method in data mining. The research process includes several critical stages, namely determining relevant data, designing a machine learning model, testing the model to ensure its effectiveness, and evaluating the model to assess the accuracy and reliability of the results. This research used sample data consisting of 92 male and female students, where the results of the analysis showed that 42 of them met the criteria to enter the superior class, while 50 other students did not. These criteria are determined based on various factors, including academic achievement, participation in extracurricular activities, and other individual characteristics assessed through the KNN method. The accuracy results obtained from the model evaluation show excellent performance, confirming that the approach used is effective in classifying students based on their potential to excel in superior class programs. The conclusion of this research shows that the use of the KNN method in data mining can accurately identify students who will benefit most from superior class programs. Thus, this approach offers a valuable tool for educational institutions to optimize student potential and raise overall standards of achievement.