Simulasi Rancangan Pemetaan Sekolah dengan Metode Algoritma Machine Learning Menggunakan Software RapidMiner

Aisyah Sabrina Aprilia, Budi Aribowo, Ahmad Chirzun

Abstract


The growth in the number of educational institutions creates competition which encourages each educational institution to have a special strategy to deal with it. The challenge that must also be faced in the world of education is the uneven quality of education in various regions. One way to face the challenge of equal distribution of school quality is to create programs that suit the needs of each school. In this study, solving the problem of mapping schools owned by the XYZ educational foundation was carried out. The results of this study obtained a design of a school mapping indicator instrument to assess the quality of each school. Then obtained a simulation of school mapping design from the results of unsupervised learning with the K-Means and K-Medoids Clustering methods, as well as a simulation of predicting school mapping patterns from the results of supervised learning with the Decision Tree C4.5 method. The results of K-Medoids were selected for the proposed school mapping with a Davies Bouldin index value of 0.112. The model cluster owned by K-Medoids, namely Excellent School, has 44 schools; at Good School, there are 36 schools; and in the Improvement School, there are 20 schools. Meanwhile, the prediction pattern with Decision Tree C4.5 obtained rules with the dominant indicator attributes (IND) 1, 2, 3, and 4. Also, the prediction simulation results using the 80:20 ratio decision tree model show the new testing data with the assumption that the 101st school goes to cluster_1 with an accuracy rate of 95%.

Keywords - Decision tree, K-means, K-medoids, School mapping indicator instrument.


Full Text:

PDF

References


D. N. L. Laksana, “Pendidikan Berkualitas dan Berkelanjutan di Era Pembelajaran Abad 21,” J. Ilm. Pendidik. Citra Bakti, vol. 5, no. 1, pp. 1–5, 2018.

G. S. Nugraha, Hairani, and R. F. P. Ardi, “Aplikasi Pemetaan Kualitas Pendidikan di Indonesia Menggunakan Metode K-Means,” J. MATRIK, vol. 17, no. 2, pp. 13–23, 2018.

N. Afifah, “Sistem Pendidikan di Indonesia,” 2020.

D. M. D. Kamayuda, “Perencanaan Strategi Bersaing Sekolah dalam Meningkatkan Jumlah Peserta Didik Baru di Salah Satu Sekolah Swasta Salatiga,” J. Manaj. Pendidik., vol. 3, no. 1, 2016.

L. Novita, “Indikkator Mutu Sekolah Menurut Perspektif Orang Tua Siswa di SMP Negeri 2 Bantul,” J. Kebijak. Pendidik., vol. VI, no. 2, pp. 184–193, 2017.

M. F. Pasaribu and R. Puspita, “Tahap Informasi, Kreatif ], dan Analisa Pada Rekayasa Nilai Untuk Meningkatkan Kualitas Pelayanan Hotel,” Ind. Eng. J., vol. 5, no. 2, pp. 46–51, 2016.

A. E. Munthafa and H. Mubarok, “Penerapan Metode Analytcal Hierarchy Process dalam Sistem Pendukung Keputusan Penentuan Mahasiswa Berprestasi,” J. Siliwangi, vol. 3, no. 2, pp. 192–201, 2017.

A. K. Wardhani, “Implementasi Algoritma K-Means untuk Pengelompokkan Penyakit Pasien pada Puskesmas Kajen Pekalongan,” J. Transform., vol. 14, no. 1, pp. 30–37, 2016.

F. Farahdinna, I. Nurdiansyah, A. Suryani, and A. Wibowo, “Perbandingan Algoritma K-means dan K-medoids dalam Klasterisasi Produk Asuransi Perusahaan Nasional,” J. Ilm. FIFO, vol. XI, no. 2, pp. 208–214, 2019.

A. Badruttamam and D. A. I. Maruddani, “Penerapan Analisis Klaster K -Modes Dengan Validasi Davies Bouldin Index Dalam Menentukan Karakteristik Kanal Youtube Di Indonesia (Studi Kasus: 250 Kanal YouTube Indonesia Teratas Menurut Socialblade ),” vol. 9, pp. 263–272, 2020.

A. F. Muhammad, “Klasterisasi Proses Seleksi Pemain Menggunakan Algoritma K-Means,” pp. 1–5, 2015.

A. P. Windarto, U. Indriani, M. R. Raharjo, and L. S. Dewi, “Bagian 1 : Kombinasi Metode Klastering dan Klasifikasi ( Kasus Pandemi Covid-19 di Indonesia ),” vol. 4, pp. 855–862, 2020.

Galih, “Data Mining di Bidang Pendidikan untuk Analisa Prediksi Kinerja Mahasiswa dengan Komparasi 2 Model Klasifikasi pada STMIK Jabar,” J. Teknol. Sist. Inf. dan Apl., vol. 2, no. 1, pp. 23–30, 2019.

P. Kasih, “Pemodelan Data Mining Decision Tree Dengan Classification Error Untuk Seleksi Calon Anggota Tim Paduan Suara,” Innov. Res. Informatics, vol. 1, no. 2, pp. 63–69, 2019.

A. A. Mahardhika, R. Saptono, and R. Anggrainingsih, “Sistem Klasifikasi Feedback Pelanggan dan Rekomendasi Soluasi Atas Keluhan di UPT PUSKOM UNS dengan Algoritma Naive Bayes Classifier dan Consine Similarity,” J. ITSMART, vol. 4, no. 1, pp. 36–42, 2015.




DOI: http://dx.doi.org/10.36722/sst.v7i1.877

Refbacks

  • There are currently no refbacks.


LP2M (Lembaga Penelitian dan Pengembangan Masyarakat)

Universitas AL-AZHAR INDONESIA, Lt.2 Ruang 207

Kompleks Masjid Agung Al Azhar

Jl. Sisingamangaraja, Kebayoran Baru

Jakarta Selatan 12110

Visitor

 This work is licensed under CC BY 4.0