Penerapan Algoritma K-Nearest Neighbor untuk Prediksi Kelulusan Siswa pada SMK Anak Bangsa

Abstract

Student graduation is very important for world education achievement, student graduation also influences the value of accreditation of an educational unit itself, therefor research on graduation prediction becomes a very interesting thing study, this study proposes the use of the K-Nearest Neighbor method to do predict student graduation at Anak Bangsa Private Vocational School. The result of the research is the value of k=5 with an accuracy rate of 93.55% which is determined as K-Optimal. The value of k=5 is applied to the K-NN algoritma to predict student graduation based on attendance, attitude, and value of knowledge.