OPTIMALISASI ALGORITMA C4.5 MENGGUNAKAN ALGORITMA GENETIKA UNTUK PREDIKSI KELULUSAN SISWA SMKN 2 CIMAHI
Abstract views: 503
,
PDF downloads: 397
Abstract
SMK 2 Cimahi is an educational institution Vocational high school in Cimahi. Vocational high schools play an important role in creating the best graduates for the needs of the workforce. The graduation process is the latest activity of student management. Student graduation criteria for national exams must meet minimum scores, complete all subjects, take school exams, national exams, and competency tests. In the 2015 class of 300 students, students who did not pass the national exam were 1 student, in the 2016 class of 299 students, students who did not pass the national exam were 1 student, whereas in the 2017 class totaling 302 students 100% students graduate on time. However in the coming year, it is still unknown whether students will be 100% graduated or not. Therefore this study was conducted to predict student graduation using the C4.5 algorithm + Genetic Algorithm. C4.5 algorithm has an accuracy rate of 99.78%, precision of 99.78%, 100% recall and 1 second execution time. While the C4.5 + genetic algorithm has an accuracy rate of 99.78%, precision of 99.78%, 100% recall AUC 0.500, and 36 second execution time and after T-test testing between the C4.5 Algorithm and C4 Algorithm .5 +, Genetic Algorithm is said to be significant if alpha = 0.050. The results of this study obtained alpha = 1,000.
References
A. Sijabat, “Penerapan Data Mining Untuk Pengolahan Data Siswa Dengan Menggunakan Metode Decision Tree ( Studi Kasus : Yayasan Perguruan Kristen Andreas),” Maj. Ilm. Inf. dan Teknol. Ilm., vol. 5, no. 3, pp. 7–12, 2015.
C. A. Sugianto, “Penerapan Teknik Data Mining Untuk Menentukan Hasil Seleksi Masuk Sman 1 Gibeber Untuk Siswa Baru Menggunakan Decision Tree,” J. TEDC, vol. 9, no. 1, pp. 39–43, 2015.
R. H. Pambudi, “Penerapan Algoritma C4.5 untuk Memprediksi Nilai Kelulusan Siswa Sekolah Menengah Berdasarkan Faktor Eksternal,” Universitas Brawijaya, 2017.
A. Rohman, “Model Algoritma K-Nearest Neighbor (K-NN) Untuk Prediksi Kelulusan Mahasiswa,” Neo Tek., vol. 1, no. 1, pp. 1–9, 2015.
S. S. Nikam, “A Comparative Study of Classification Techniques in Data Mining Algorithms,” Int. J. Mod. Trends Eng. Res., vol. 4, no. 7, pp. 58–63, 2017.
S. Maslahah, “Prediksi Kelulusan Mahasiswa Menggunakan Metode Decision Tree Dengan Penerapan Algoritma C4.5,” Universitas Islam Negeri Maulana Malik Ibrahim, 2013.
M. A. Kartika, “Pencocokan Kata Secara Acak Dengan Metode Algoritma Genetika Menggunakan Program Pascal,” J. Matametika, vol. 2, no. 2, pp. 1–9, 1975.
I. Ali, L. Sularto, D. Sudrajat, D. A. Kurnia, and Y. A. Wijaya, “Optimasi Parameter Artificial Neural Network Menggunakan Algoritma Genetika Untuk Prediksi Kelulusan Mahasiswa,” J. ICTInformation Commun. Technol., vol. 18, no. 1, pp. 54–59, 2019.
B. D. Meilani and N. Susanti, “Aplikasi Data Mining Untuk Menghasilkan Pola Kelulusan Siswa Dengan Metode Naïve Bayes,” J. Ilm. NERO, vol. 1, no. 3, pp. 182–189, 2015.
Copyright (c) 2019 Infotekmesin
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
