Analysis of the Effect of Attributes on Single Tuition Fee Grouping Using Multiple Linear Regression and Extreme Gradient Boosting

Dea Annova Prayetno Putri; Erna Budhiarti  Nababan; Mohammad Andri  Budiman

doi:10.53623/gisa.v6i2.1289

Objectively determining the Single Tuition Fee (UKT) level was essential for aligning educational costs with students’ socioeconomic conditions. This study compared Multiple Linear Regression (MLR) and Extreme Gradient Boosting (XGBoost) for predicting the final (Pleno) UKT level using data from 12,355 students, including socioeconomic, school-related, and administrative attributes. Data preprocessing involved cleaning, handling missing values and duplicates, transforming categorical variables, and splitting the dataset into training and testing sets (80:20). Models were evaluated under “operational” and “strict” scenarios using accuracy, precision, recall, F1-score, confusion matrices, and AUC. In the operational scenario, XGBoost achieved 93.42% training and 90.15% testing accuracy, outperforming MLR, which achieved 84.10% testing accuracy. Under the strict scenario, XGBoost accuracy decreased to 63.27–63.54%, compared with 49.74–49.86% for MLR. These findings demonstrated XGBoost’s greater ability to capture nonlinear relationships and complex attribute interactions. Permutation importance identified Coordinator- and Verifier-assigned UKT as the dominant predictors, while SHAP analysis identified per capita income as the most influential socioeconomic factor. Overall, XGBoost showed superior predictive performance but should be used as a decision-support tool rather than as the sole determinant of student tuition fees.

Read Full-Text

Previous article

Next article

References

Raiya, M.S.; Khamil, M.R.P.; Fadillah, N.; Saputra, R.A. (2025). Implementasi Algoritma Long Short-Term Memory pada Isu Kenaikan Uang Kuliah Tunggal terhadap Minat Kuliah Mahasiswa. Jurnal Informatika Terpadu, 11(1), 37–43. https://doi.org/10.54914/jit.v11i1.1656.

Susetyoko, R.; Yuwono, W.; Purwantini, E.; Ramadijanti, N. (2022). Perbandingan Metode Random Forest, Regresi Logistik, Naïve Bayes, dan Multilayer Perceptron pada Klasifikasi Uang Kuliah Tunggal (UKT). Jurnal Infomedia: Teknik Informatika, Multimedia & Jaringan, 7(1), 8–16. https://doi.org/10.30811/jim.v7i1.2916.

Wardani, A.N.; Olfah, S.T.; Santoso, K.; Wahyudi, A. (2025). Uang Kuliah Tunggal (UKT) sebagai Penerimaan Negara Bukan Pajak (PNBP): Persepsi Mahasiswa pada PTN dan PTKIN BLU. Jurnal Info Artha, 9(1), 49–77. https://doi.org/10.31092/jia.v9i1.3343.

Sukamto, S.; Adriyani, Y.; Aulia, R. (2020). Prediksi Kelompok UKT Mahasiswa Menggunakan Algoritma K-Nearest Neighbor. JUITA: Jurnal Informatika, 8(1), 121–130. https://doi.org/10.30595/juita.v8i1.6267.

Triase, T.; Samsudin, S. (2020). Implementasi Data Mining dalam Mengklasifikasikan UKT (Uang Kuliah Tunggal) pada UIN Sumatera Utara Medan. Jurnal Teknologi Informasi, 4(2), 370–376. https://doi.org/10.36294/jurti.v4i2.1711.

Cheng, X.; Guo, Y.; Gao, J.; Chen, Y.; Pan, G. (2023). Coordinated Passive Maneuvering Target Tracking by Multiple Underwater Vehicles Based on Asynchronous Sequential Filtering. International Conference on Intelligent Robotics and Applications; Springer, pp. 246–255.

Rohman, M.G.; Abdullah, Z.; Kasim, S.; Albab, M.U. (2026). Machine Learning to Identify Eligibility of Students Receiving Single Tuition Relief. JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), 11(3), 613–626. https://doi.org/10.33480/jitk.v11i3.7294.

Siddique, A.; Jan, A.; Majeed, F.; Qahmash, A.I.; Quadri, N.N.; Wahab, M.O.A. (2021). Predicting Academic Performance Using an Efficient Model Based on Fusion of Classifiers. Applied Sciences, 11, 11845. https://doi.org/10.3390/app112411845.

Li, W.; Yin, Y.; Quan, X.; Zhang, H. (2019). Gene Expression Value Prediction Based on XGBoost Algorithm. Frontiers in Genetics, 10, 1077. https://doi.org/10.3389/fgene.2019.01077.

Wang, S.; He, J. (2025). Evaluating and Forecasting Undergraduate Dropouts Using Machine Learning for Domestic and International Students. Technologies, 13, 480. https://doi.org/10.3390/technologies13110480.

Wahyuani, A.S. (2018). Pemilihan Parameter Terbaik Menggunakan Metode ID3 untuk Penentuan Cluster Terbaik pada Metode K-Means Clustering: Studi Kasus Penentuan Golongan Uang Kuliah Tunggal Universitas Islam Negeri Maulana Malik Ibrahim. Thesis, Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia.

Sari, S.D. (2025). Analisis Faktor Penentuan Golongan UKT di UIN Maulana Malik Ibrahim Malang Menggunakan Regresi Probit Ordinal. Thesis, Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia.

Sheng, C.; Yu, H. (2022). An Optimized Prediction Algorithm Based on XGBoost. In 2022 International Conference on Networking and Network Applications (NaNA); IEEE, pp. 1–6. https://doi.org/10.1109/NaNA56854.2022.00082.

Gajdzik, B.; Wolniak, R.; Sączewska-Piotrowska, A.; Grebski, W.W. (2025). Polish Steel Production under Conditions of Decarbonization—Steel Volume Forecasts Using Time Series and Multiple Linear Regression. Energies, 18(7), 1627. https://doi.org/10.3390/en18071627.

Read Full-Text

About this article

SUBMITTED: 07 July 2026
ACCEPTED: 20 August 2026
PUBLISHED: 30 August 2026
SUBMITTED to ACCEPTED: 45 days
DOI: https://doi.org/10.53623/gisa.v6i2.1289

Cite this article

Prayetno Putri, D. A., Nababan, E. B. ., & Budiman, M. A. . (2026). Analysis of the Effect of Attributes on Single Tuition Fee Grouping Using Multiple Linear Regression and Extreme Gradient Boosting. Green Intelligent Systems and Applications, 6(2), 217−230. https://doi.org/10.53623/gisa.v6i2.1289

Citations

Share this article

Analysis of the Effect of Attributes on Single Tuition Fee Grouping Using Multiple Linear Regression and Extreme Gradient Boosting

Green Intelligent Systems and Applications

Volume 6 - Issue 2 - 2026

Abstract

References