THE PREDICTION OF THE GRADUATION RATE ON TIME WITH THE METHODS NAÏVE BAYES AND K-NEAREST NEIGHBOR
Graduates is status reached students after completing the process of education in accordance with the requirements of graduation set by the study program. As one of the output is to directly from the process of education that have been undertaken by by the study program , a graduate of a who are fully dedicated rewarded with lofty mansions in academic pt batubara bukit kendi total competence including a hard skills the and soft skills the as claimed in the target group quality and shall be proven with the performance of a graduate of a in the midst of society in accordance with for a profession and the field of science. Course of study quality having management systems good graduates order to be able to make them a human capital for successor program study concerned.
This research uses the data mining used to measure graduation rates students using two method is naive bayes and k-nearest neighbor. The result of this research to predict students just pass or late.The trial was done using data from information system undergraduates stmik dian cipta cendikia kotabumi about 600 data for training and 180 data for testing The results of the tryouts shows that by the use of naïve bayes produce of accuracy of the numbers bayes as much as 85 % , while using an algorithm k-nearest neighbor produce of accuracy of the numbers as much as 68.89 %.
 BAN-PT, B. A., 2010, AKREDITASI PROGRAM STUDI DIPLOMA. Jakarta: BAN-PT.
 Windarti, M., 2016, Prediksi Masa Studi Mahasiswa Menggunakan Kombinasi Algoritma Bayesian Network Dan K-Nearest Neighbors (Doctoral dissertation, UAJY).
 Lumenta, A.S. and Jacobus, A., 2017. Prediksi Masa Studi Mahasiswa dengan Menggunakan Algoritma Naïve Bayes. JURNAL TEKNIK INFORMATIKA UNIVERSITAS SAM RATULANGI, 11(1).
 Novianti, A.G. and Prasetyo, D., PENERAPAN ALGORITMA K-NEAREST NEIGHBOR (K-NN) UNTUK PREDIKSI WAKTU KELULUSAN MAHASISWA.
 Ginting, S.L.B., Zarman, W. and Darmawan, A., 2014. Teknik Data Mining Untuk Memprediksi Masa Studi Mahasiswa Menggunakan Algoritma K-Nearest Neighborhood. Jurnal Teknik Komputer Unikom, 3(2), pp.29-34.