PENENTUAN TINGKAT KELULUSAN TEPAT WAKTU MAHASISWA STMIK SUBANG MENGGUNAKAN ALGORITMA C4.5

Hermansyah Nur Ahmad
Vincent Suhartono
Ika Novita Dewi

Jurnal Teknologi Informasi Cyberku
Vol 13 No 1 (2017): Jurnal Teknologi Informasi CyberKU Vol. 13, no 1

Timely graduatuion rates in college could not be consideres easy and trivial. Many cases found that the share of the number of students who did not get in and who have completed their studies so that the build up of high numbers of students in every period. I need to know the factors cause students not graduating on time. Classification data mining techniques can be used to predict student graduation rates. The algorithm used is algoritmic C 4.5 with data as much as 200 students study computer engineering programs STMIK Subang. The result of the classification process is evaluated by using the confusion matrix, ROC Curve, Recall. Based on experimental results and evluation is done then it can be inferred that the algorithm C 4.5 accurately applied to determine the level of students graduation. After testing the prediction accuracy resulting from trials reached 95,00% of the classification result generate information in the from of graph in the form of the curve results from the decision tree that is useful for institutions of higher education in taking policy.