A Data-Driven Approach to Building a Student Graduation Map with the K-Nearest Neighbors Algorithm at Hayam Wuruk Perbanas University

Yudha Herlambang Cahya Pratama; Laqma Dica Fitrani; Muhammad Septama Prasetya

doi:10.34148/teknika.v14i3.1282

Authors

Yudha Herlambang Cahya Pratama Departement of Information System, Faculty of Engineering and Design, Hayam Wuruk Perbanas University, Surabaya, East Java, Indonesia
Laqma Dica Fitrani Department of Digital Business, Faculty of Computer Science, Universitas Pembangunan Nasional Veteran Jawa Timur, Surabaya, East Java, Indonesia
Muhammad Septama Prasetya Department of Information Systems, Faculty of Computer Science, Universitas Pembangunan Nasional Veteran Jawa Timur, Surabaya, East Java, Indonesia

DOI:

https://doi.org/10.34148/teknika.v14i3.1282

Keywords:

Academic Data, Classification, Data Mining, Machine Learning, KKN

Abstract

This study addresses the underutilization of student academic data at Universitas Hayam Wuruk Perbanas Surabaya, despite a significant trend of over 50% of students graduating within 3.5 years—raising important questions about academic quality assurance. To respond to this, the study aims to develop a data-driven graduation map by applying the K-Nearest Neighbors (KNN) algorithm to classify students based on their likelihood of graduating on time or late. Using historical academic records from 316 students of the 2022 cohort, the methodology involved data preprocessing, feature selection, implementation in RapidMiner, and algorithm testing. The KNN model was evaluated using a 70:30 training-to-testing split. Results demonstrated strong predictive performance of ROC (Receiver Operating Characteristic), including 95.74% accuracy, 100% precision for predicting delayed graduation, and an AUC (Area Under Curve) of 0.969. While the model was highly effective in identifying on-time graduates, it exhibited slightly lower recall for late graduates. These findings offer practical implications for developing targeted academic support systems and contribute to the broader application of machine learning in higher education analytics in Indonesia. Limitations include the use of data from a single cohort and reliance on one algorithm; future research may explore multi-cohort data and compare multiple classification methods to enhance generalizability and robustness.

Downloads

Download data is not yet available.

References

[1] OECD, “Higher Education,” 2024. https://www.oecd.org/en/topics/higher-education.html.

[2] R. Pratama, R. Herdiana, R. Hamonangan, and S. Anwar, “Analisis Prediksi Kelulusan Mahasiswa Menggunakan Metode Artificial Neural Network,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 1, pp. 687–693, 2024, doi: 10.36040/jati.v8i1.8762.

[3] A. Marwah, “A Study Of Factors Influencing Students In Selecting Higher Education Institutions -A Literature Review,” Dogo Rangsang Res. J., vol. 122, no. 12, pp. 162–171, 2022.

[4] S. S. Akbar et al., Pengantar Bisnis Strategi Inovatif di Era Digital, Pertama. Purbalingga: Eurika Media Aksara, 2024.

[5] Supriyono et al., Sistem Informasi Manajemen. Purbalingga: Eureka Media Aksara, 2024.

[6] J. M. Polgan et al., “Optimasi Prediksi Kelulusan Mahasiswa Menggunakan Random Forest untuk Meningkatkan Tingkat Retensi,” Jurnal Minfo Polgan, vol. 13, pp. 2364–2374, 2025. doi :10.33395/jmp.v13i2.14472

[7] R. Sakti and A. Daulay, “Analisis Kritis dan Pengembangan Algoritma K-Nearest Neighbor ( KNN ): Sebuah Tinjauan Literatur,” Jurnal Pendidikan Sains dan Komputer, vol. 4, no. 2, pp. 131–141, 2024. doi: 10.47709/jpsk.v4i02.

[8] Z. Hadiansyah, Z. Rozikin, and M. Fatchan, “Implementasi Algoritma K-Nearest Neighbor Dalam Klasifikasi Penyakit Kanker Paru Paru,” Journal of Computer System and Informatics, vol. 6, no. 1, pp. 96–106, 2024, doi: 10.47065/josyc.v6i1.6195.

[9] M. Utami and V. Ayumi, “Prediksi Penjualan Produk Terlaris Menggunakan Algoritma K-Nearest Neighboard ( KNN ),” Journal Computer Science and Information Syetem, vol. 1, no. 2, pp. 43–47, 2024. doi:10.61567.

[10] M. Jawthari and V. Stoffová, “Predicting students’ academic performance using a modified kNN algorithm,” Pollack Period., vol. 16, no. 3, pp. 20–26, 2021, doi: 10.1556/606.2021.00374.

[11] A. Suzana, B. Lomi, A. A. Pekuwali, and R. T. Abineno, “Pengelompokan Mahasiswa Berpotensi Drop Out Pada Program Studi Teknik Infromatika Menggunakan Metode K-Means Clustering,” pp. 340–351, 2024. https://ojs.unkriswina.ac.id/index.php/semnas-FST.

[12] F. R. Yudana, M. Suyanto, and A. Nasiri, “Model Klasifikasi Untuk Menentukan Kesiapan Kerja Mahasiswa Dan Kelulusan Tepat Waktu Dengan Metode Machine Learning,” IJITECH Indones. J. Inf. Technol., vol. 1, no. 1, pp. 1–12, 2023, doi: 10.37680/ijitech.v1i1.xx.

[13] R. Mubarak, M. Hanafi, and D. Sasongko, “Komparasi Performa Naive Bayes Gaussian dan K-NN Untuk Prediksi Kelulusan Mahasiswa dengan CRISP-DM,” KLIK Kaji. Ilm. Inform. dan Komput., vol. 4, no. 6, pp. 2982–2991, 2024, doi: 10.30865/klik.v4i6.1924.

[14] S. A. Mohamed Yusoff, J. Othman, A. Mohd Mydin, W. A. Wan Mohamad, E. J. Johan, and A. F. Mohamed Yusoff, “Students’ Academic Performance: Prediction using Machine Learning Approaches,” Int. J. Acad. Res. Progress. Educ. Dev., vol. 13, no. 3, pp. 1778–1792, 2024, doi: 10.6007/ijarped/v13-i3/22164.

[15] L. K. Smirani, H. A. Yamani, L. J. Menzli, and J. A. Boulahia, “Using Ensemble Learning Algorithms to Predict Student Failure and Enabling Customized Educational Paths,” Sci. Program., vol. 2022, 2022, doi: 10.1155/2022/3805235.

[16] O. Ojajuni et al., Predicting Student Academic Performance Using Machine Learning, vol. 12957 LNCS, no. September. Springer International Publishing, 2021. 10.1109/ISRITI48646.2019.9034585.

[17] R. Rismala, I. Ali, and A. Rizki Rinaldi, “Penerapan Metode K-Nearest Neighbor Untuk Prediksi Penjualan Sepeda Motor Terlaris,” JATI (Jurnal Mhs. Tek. Inform., vol. 7, no. 1, pp. 585–590, 2023, doi: 10.36040/jati.v7i1.6419.

[18] J. Astri, J. Karman, and N. K. Daulay, “Prediksi Kelulusan Mahasiswa Menggunakan Metode K-Nearest Neigbor (KNN) pada Fakultas Ilmu Teknik, Univeritas Bina Insan,” J. Ris. Sist. Inf. Dan Tek. Inform., vol. 8, pp. 169–173, 2023, https://tunasbangsa.ac.id/ejurnal/index.php/jurasik. doi: 10.30645/jurasik.v8i1.552.

[19] U. Putra and I. Yptk, “Penerapan algoritma klasifikasi untuk prediksi tingkat kelulusan mahasiswa menggunakan rappidminer,” vol. 6, no. 1, pp. 376–388, 2025, doi: 10.46576/djtechno.

[20] S. Sumarlin and D. Anggraini, “Implementasi K-Nearest Neighbord Pada Rapidminer Untuk Prediksi Kelulusan Mahasiswa,” High Educ. Organ. Arch. Qual. J. Teknol. Inf., vol. 10, no. 1, pp. 35–41, 2018, doi: 10.52972/hoaq.vol10no1.p35-41.

[21] N. K. Di et al., “Gudang Jurnal Multidisiplin Ilmu Prediksi Kelulusan Siswa Menggunakan Algoritma K- Nearest,” vol. 2, no. November, pp. 110–115, 2024. doi: 10.59435/gjmi.v2i11.1050.