AKADEMIK DATA MINING (ADM) K-MEANS DAN K-MEANS K-NN UNTUK MENGELOMPOKAN KELAS MATA KULIAH KOSENTRASI MAHASISWA SEMESTER AKHIR

• Main Authors: Suhardi Rustam, Haditsah Annur
• Format: Article
• Language: English
• Published: Fakultas Ilmu Komputer UMI 2019-12-01
• Series: Ilkom Jurnal Ilmiah
• Subjects: academic data mining; k-means; k-nn; auc accuracy
• Online Access: http://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/487

University as an educational institution plays an important role in producing graduates. In addition, institutions such as universitas ichsan Gorontalo save the data set. These Data include about student academic data.In the academic field, every semester, increasing the amount of data recorded with data from academic activities. It is like there is a Tsunami of data which indicate that these data are very abundant but do not give any knowledge that is not beneficial to the university, especially the faculty except the knowledge administrative. Universitas ichsan Gorontalo with the number of students reached 9000 people which is accompanied by the number of graduates is still less than ideal any period graduate, it is necessary to apply the pattern determination grade concentration courses effective for the achievement ability of students, academic Data will be used namely the data of the students 2016-2017 who has taken class subjects concentration. The application of K-Means algorithm and K-Means KNN where K=2 result in a cluster for grouping of a Class Focus on the students semester end and each cluster has a predictive value for the second klustering such, the Value of the resulting Accuracy of Algorithms KNN, namely the AUC (Area Under The Curve) =1, the Value of CA=1, the value of F1=1, the value of the precision=1 and recall=1, and the value of accuracy as the best value.