Rizky Aspiah
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

IMPLEMENTASI CORRELATION BASED FEATURE SELECTION (CFS) UNTUK PENINGKATAN AKURASI ALGORITMA C4.5 DALAM PREDIKSI PERFORMA AKADEMIK MAHASISWA BERBASIS LEARNING MANAGEMENT SYSTEM Rizky Aspiah; Taghfirul Azhima Yoga Siswa
JURNAL ILMIAH BETRIK : Besemah Teknologi Informasi dan Komputer Vol 13 No 2 (2022): JURNAL ILMIAH BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : LPPM Sekolah Tinggi Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/betrik.v13i2.523

Abstract

The COVID-19 pandemic in the education aspect has an impact on the learning system. Muhammadiyah University of East Kalimantan utilizes the OpenLearning platform as a medium to support online learning. In this study, predictions of the performance of UMKT students in online lectures were carried out using a data mining approach. The dataset used comes from the OpenLearning platform and the Academic Administration Section which contains 2,663 data. This study aims to identify the best attributes, implement the C4.5 algorithm modeling, and search for modeling searches using a confusion matrix. The results showed that the influential indicators included time spent on courses, completed courses, assignments, quizzes, uts and labels. The implementation of the C4.5 algorithm produces a decision tree at the initial node of the quiz variable with a rank of -0.80 which is included in the true group, but if the rank is -0.80 it is included in the false group. The results of the accuracy using the distribution data of 80% training data and 20% testing data are 97.22%.