Prediksi Kelulusan dan Putus Studi Mahasiswa dengan Pendekatan Bertingkat pada Perguruan Tinggi

Currently, the problem of college failure, its on-time graduation, and factors that cause it is still an interesting research topic (C. Marquez-Vera, C. Romero S. Ventura, 2011). This study compares three data mining classification algorithms namely Naive Bayes, Decision Tree K-Nearest Neighbor to predict graduation dropout risk for students improve quality higher education most accurate use Prepare prediction Student studies. The best algorithm predicting decision tree with accuracy value 99.15% a training ratio 30%. Keyword : Data Mining; Algoritma Bayes; Tree; Neighbor; Predict Graduation; Drop Out.