Prediksi Status Keaktifan Studi Mahasiswa dengan Algoritme C5.0 dan K-Nearest Neighbor
MetadataShow full item record
Data mining methods are required to explore pyramid of data such that strategic information is uncovered. In this thesis, data mining techniques are used to find student characteristics whom is active or inactive academically. Further, these characteristics can be employed to classify students based on their academic status one semester in advance. This research made use an open source data mining application software named WEKA Classifier. The experimental results showed that C5.0 Algorithm is better than KNN and Grade Point Average (GPA) contributes significantly in determining next coming semester student status.