Implementation Of Decision Tree And K-NN Classification Of Interest in Contiuning Student School

Implementation Of Decision Tree And K-NN Classification Of Interest in Contiuning Student School

• By Saputri, Daniati Uki Eka Saputri; Nugraha, Fitra Septia; Hidayat, Taopik; Latif, Abdul; Suryadi, Ade; Pohan, Achmad Baroqah;
• Jurnal Nasional Terakreditasi
• 256
• 51-56

Education is important to prepare quality Human Resources (HR) because quality human resources is an important factor for the nation and state development. Therefore, it is expected that every citizen has the right to get high educational opportunities from the 12-year compulsory education level. This study aims to implement the Decision Tree and K-NN algorithm in the classification of student interest in continuing school.  This study proposes combining the Decision Tree and K-NN algorithm methods to improve accuracy with the Gain Ratio, Information Gain and Gini Index approaches for the measurement process. The test results show that the use of the Decision Tree algorithm produces an accuracy value of 97.30% while using the K-NN algorithm produces an accuracy of 89.60%. While the proposed method by combining the Decision Tree and K-NN algorithms produces an accuracy value of 98.07%. The results of evaluation measurements using the Area Under Curve (AUC) on the Decision Tree algorithm are 0.992 and the AUC on K-NN is 0.958 and on the combination of the Decision Tree and K-NN algorithms of 0.979. These results indicate that the proposed algorithm is very significant towards increasing accuracy in the classification of the interests of high school students continuing school

• Katakunci Accuracy, Classification, Interest, Decision Tree, K-NN
• URL http://ejournal.nusamandiri.ac.id/index.php/techno/article/view/1289
• Penerbit ,

REFERENSI

Arifin, A. A., & Ratnasari, S. (2017). Hubungan Minat Melanjutkan Pendidikan ke Perguruan Tinggi dengan Motivasi Belajar Siswa. JURKAM: Jurnal Konseling Andi Matappa, 1(1), 77–82. https://journal.stkip-andi-matappa.ac.id/index.php/jurkam/article/view/9

Badan Pusat Statistik. (2017). Potret Pendidikan Indonesia Statistik Pendidikan. Badan Pusat Statistik.

Dervisevic, O., Zunic, E., Donko, D., & Buza, E. (2019). Application of KNN and Decision Tree Classification Algorithms in the Prediction of Education Success from the Edu720 Platform. 2019 4th International Conference on Smart and Sustainable Technologies, SpliTech 2019. https://doi.org/10.23919/SpliTech.2019.8783102

Peraturan Pemerintah Republik Indonesia Nomor 47 Tahun 2008 Tentang Wajib Belajar, Pub. L. No. 47, 10 (2008). https://peraturan.bpk.go.id/Home/Details/4861/pp-no-47-tahun-2008

Muhammad, M. (2017). PENGARUH MOTIVASI DALAM PEMBELAJARAN. Lantanida Journal, 4(2), 87–97. https://jurnal.ar-raniry.ac.id/index.php/lantanida/article/view/1881

Nugroho, M. F., & Wibowo, S. (2017). Fitur Seleksi Forward Selection Untuk Menetukan Atribut Yang Berpengaruh Pada Klasifikasi Kelulusan Mahasiswa Fakultas Ilmu Komputer UNAKI Semarang Menggunakan Algoritma Naive Bayes. Jurnal Informatika Upgris, 3(1), 63–70. https://doi.org/10.26877/jiu.v3i1.1669

Prasojo, L. D., Mukminin, A., & Mobmudoh, F. N. (2018). Manajemen Human Capital dalam Pendidikan.

Sadewo, M. G., Windarto, A. P., & Wanto, A. (2018). Penerapan Algoritma Clustering Dalam Mengelompokkan Banyaknya Desa/Kelurahan Menurut Upaya Antisipasi/ Mitigasi Bencana Alam Menurut Provinsi Dengan K-Means. KOMIK (Konferensi Nasional Teknologi Informasi Dan Komputer), 2(No.1 Oktober 2018), 311–319. https://doi.org/10.30865/komik.v2i1.943

Saputri, D. U. E., Nugraha, F. septia, Hidayat, T., Latif, A., Suryadi, A., & Pohan, A. B. (2020). Final Report of Independent Research: Implementation of Decision Tree and K-NN in the Classification of Student Interest Level Continuing School.

Suyitno, F. A. (2016). Faktor-Faktor Yang Mempengaruhi Minat Siswa Untuk Melanjutkan Studi SMK Jurusan TKR di SMP N 34 Purworejo. Jurnal Autotech, 8(2), 113–118. http://ejournal.umpwr.ac.id/index.php/autotext/article/view/3112