Implementasi Algoritma K-Nearest Neighbor untuk Klasifikasi Jurusan pada Peserta Didik Baru

Abstract

Majoring students is a process of placing students into certain majors in accordance with their interests and academic abilities in an effort to make it easier for students in the learning process. Madrasah Aliyah Darul Hikmah Menganti is a school equivalent to SMA, which has two majors, namely science and social studies. The difficulty of classifying the majors of new students is an obstacle for the school. Because the criteria assessment process is carried out one by one. From these problems, the K-Nearest Neighbor (K-NN) method was applied to classify majors in order to simplify and minimize errors in the process of determining new student majors. The data initially amounted to 638 records and 31 attributes. After preprocessing, the data used amounted to 635 records with 12 attributes, namely name, gender, major interest, school origin, children to, number of siblings, math scores, English grades, science grades, Indonesian language scores, test scores, and major recommendations. After testing using K-Fold Cross Validation and Confusion Matrix for evaluation and validation of results by calculating the Euclidean Distance distance, the best k value (optimal) k=3 which produces accuracy: 97.11%, precision: 96.82%, recall: 98.33%, and AUC: 0.951.