CLASSIFICATION OF VOCATIONAL HIGH SCHOOL GRADUATES' ABILITY IN INDUSTRY USING EXTREME GRADIENT BOOSTING (XGBOOST), RANDOM FOREST, AND LOGISTIC REGRESSION

Afikah Agustiningsih; Yulian Findawati; Irwan Alnarus Kautsar

doi:10.52436/1.jutif.2023.4.4.945

Afikah Agustiningsih Informatics, Faculty of Science and Technology, Universitas Muhammadiyah Sidoarjo, Indonesia
Yulian Findawati Informatics, Faculty of Science and Technology, Universitas Muhammadiyah Sidoarjo, Indonesia
Irwan Alnarus Kautsar Informatics, Faculty of Science and Technology, Universitas Muhammadiyah Sidoarjo, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2023.4.4.945

Keywords: Classification, graduate quality, machine learning, vocational high school (SMK)

Abstract

The education world is one of the main sources in producing Human Resources. Vocational High School (SMK) is one level of school that presents various majors that are ready to compete in the industrial world. Therefore, a school institution needs to have a system to determine the quality of education provided to students so that they can compete in the industrial world. This study designs a system that is capable of classifying SMK student graduates as an evaluation for the school institution. The goal is to enable the school to devise strategies for producing better student quality in the following year. There are four classes in this study, namely those who work, those who are not working yet, those who are in college, and those who are entrepreneurs. There are several stages in building the classification system, including pre-processing, processing, and evaluation. This research uses three machine learning algorithms, namely XGBoost, Random Forest, and Logistic Regression. The results of the three methods obtained a training score of 91.70%, a test score of 66.88%, and an accuracy score of 67% generated by the XGBoost algorithm. The Random Forest algorithm produced a training score of 97.36%, a test score of 68.71%, and an accuracy score of 67%. Meanwhile, Logistic Regression produced a training score of 51.14%, a test score of 50.43%, and an accuracy score of 50%.

Downloads

Download data is not yet available.

References

Y. Sangsurya, M. Muazza, and R. Rahman, “Perencanaan Sumber Daya Manusia Dalam Peningkatan Mutu Pendidikan Di Sd Islam Mutiara Al Madan Kota Sungai Penuh,” J. Manaj. Pendidik. Dan Ilmu Sos., vol. 2, no. 2, pp. 766–778, 2021, doi: 10.38035/jmpis.v2i2.644.

S. A. Nurfatimah, S. Hasna, and D. Rostika, “Membangun Kualitas Pendidikan di Indonesia dalam Mewujudkan Program Sustainable Development Goals (SDGs),” J. Basicedu, vol. 6, no. 4, pp. 6145–6154, 2022, doi: 10.31004/basicedu.v6i4.3183.

H. Priyono, R. Sari, and T. Mardiana, “Klasifikasi Pemilihan Jurusan Sekolah Menengah Kejuruan Menggunakan Gradient Boosting Classifier,” J. Inform., vol. 9, no. 2, pp. 131–139, 2022, doi: 10.31294/inf.v9i2.12654.

L. W. Kusuma, “Prediksi Kemampuan Lulusan SMK untuk Dapat Bersaing Di Dunia Kerja dengan Menggunakan Naïve Bayes : Studi Kasus SMK Buddhi Tangerang,” Prediksi Kemamp. Lulusan SMK untuk Dapat Bersaing Di Dunia Kerja dengan Menggunakan Naïve Bayes Stud. Kasus SMK Buddhi Tangerang, vol. 1, pp. 56–63, 2019.

Y. Septiani and P. F. Ariyani, “Penerapan Algoritma Naive Bayes Menentukan Klasifikasi Tingkat Kelulusan Siswa SMK Media Informatika Jakarta Application of The Naive Bayes Algorithm Determining Classification of Students ’ Graduation Level of Jakarta Media Informatika Vocational School,” no. September, pp. 607–613, 2022.

E. Purwaningsih and E. Nurelasari, “Penerapan K-Nearest Neighbor Untuk Klasifikasi Tingkat Kelulusan Pada Siswa,” Syntax J. Inform., vol. 10, no. 01, pp. 46–56, 2021, doi: 10.35706/syji.v10i01.5173.

I. Muslim and K. Karo, “Implementasi Metode XGBoost dan Feature Importance untuk Klasifikasi pada Kebakaran Hutan dan Lahan,” J. Softw. Eng. Inf. Commun. Technol., vol. 1, no. 1, pp. 10–16, 2020.

M. Rizky Mubarok, Muliadi, and R. Herteno, “Hyper-Parameter Tuning pada XGBoost Untuk Prediksi Keberlangsungan Hidup Pasien Gagal Jantung,” Kumpul. J. Ilmu Komput., vol. 9, no. 2, pp. 391–401, 2022.

P. R. Sihombing and I. F. Yuliati, “Penerapan Metode Machine Learning dalam Klasifikasi Risiko Kejadian Berat Badan Lahir Rendah di Indonesia,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 20, no. 2, pp. 417–426, 2021, doi: 10.30812/matrik.v20i2.1174.

A. K. Santoso, A. Noviriandini, A. Kurniasih, B. D. Wicaksono, and A. Nuryanto, “Klasifikasi Persepsi Pengguna Twitter Terhadap Kasus Covid-19 Menggunakan Metode Logistic Regression,” JIK (Jurnal Inform. dan Komputer), vol. 5, no. 2, pp. 234–241, 2021.

A. Tjalla and M. Mahdiyah, “Data Kategorik dalam Penelitian : Review Bibliometrik,” vol. 9, no. 1, pp. 796–802, 2023, doi: 10.58258/jime.v9i1.4814/http.

A. N. Kasanah, M. Muladi, and U. Pujianto, “Penerapan Teknik SMOTE untuk Mengatasi Imbalance Class dalam Klasifikasi Objektivitas Berita Online Menggunakan Algoritma KNN,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 3, no. 2, pp. 196–201, 2019, doi: 10.29207/resti.v3i2.945.

D. A. Nasution, H. H. Khotimah, and N. Chamidah, “Perbandingan Normalisasi Data untuk Klasifikasi Wine Menggunakan Algoritma K-NN,” Comput. Eng. Sci. Syst. J., vol. 4, no. 1, p. 78, 2019, doi: 10.24114/cess.v4i1.11458.

E. Agustin, A. Eviyanti, and N. L. Azizah, “Deteksi Penyakit Epilepsi Melalui Sinyal EEG Menggunakan Metode DWT dan Extreme Gradient Boosting,” vol. 7, pp. 117–127, 2023, doi: 10.30865/mib.v7i1.5412.

M. Noveanto, H. Sastypratiwi, and H. Muhardi, “Uji Akurasi Klasifikasi Emosi Pada Lirik Lagu Bahasa Indonesia Emotion Classification Accuracy Test in Indonesian Song Lyrics,” vol. 10, no. 3, pp. 311–318, 2022, doi: 10.26418/justin.v10i3.56804.