@thesis{thesis,
		author={Kusuma  Ecak Nyoman Purnamaning},
		title ={PREDIKSI MAHASISWA DROPOUT MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOUR (KNN)},
		year={2021},
		url={http://repository.universitasbumigora.ac.id/854/},
		abstract={STAHN is one of the State Hindu Religious Colleges in Mataram City. At the college there are students who have dropped out. Students who dropout at the college are not the least due to the student's work and marital status, the study program has difficulty in overcoming this dropout problem, therefore this research is carried out with the aim of helping the study program to overcome and minimize the occurrence of dropout students and implement the K algorithm -Nearest Neighbor in predicting student dropouts. The solution in overcoming these problems, the authors use the K-Nearest Neighbor algorithm which is one of the data mining techniques included in the classification to predict dropout students at the college. and building a desktop application to implement the K-Nearest Neighbor algorithm in the application, and testing is done using confusion matrix. The confusion matrix is used to test the accuracy of the K-Nearest Neighbor algorithm on dropout student problems. The results obtained from this study are in the form of a student droput prediction system using the K-Nearest Neighbor algorithm and obtaining accuracy using the k = 3 value of 97.28%, k = 5 of 97.05%, and k = 7 of 97.06%. the best k value depends on the data and a high k value will reduce the effect of noise on the classification. It can be concluded from this study that the system built is used to predict dropout students and the test results using the K-Nearest Neighbor algorithm show the highest level of accuracy is found at k = 3 with a percentage of 97.28%.}
		}