Optimization of Student Graduation Timeliness Prediction at Royal University Using Particle Swarm Optimization-Based Naive Bayes Algorithm
Keywords:
Naive Bayes, Particle Swarm Optimization, Graduation Timeliness, Feature Selection, Royal UniversityAbstract
Graduation timeliness is a primary indicator in the accreditation assessment of higher education institutions. Royal University faces complexities in monitoring student graduation trends due to the vast volume of heterogeneous academic data. This study aims to enhance the performance of graduation timeliness prediction by implementing Feature Selection optimization using the Particle Swarm Optimization (PSO) algorithm on Naive Bayes classification. The dataset successfully extracted comprises 4,909 observations of alumni academic records, utilized to ensure the validity of target label attribution (On-time vs. Delayed). The PSO optimization process is employed to reduce irrelevant features that may degrade model performance. The research results indicate that the integration of PSO significantly improves accuracy from 79.55% in the standard Naive Bayes algorithm to 87.16% in the optimized model. The dominant selected features include School Origin, Final GPA, and Attendance Rate. These findings prove that the hybrid PSO-Naive Bayes model is effective as an Early Warning System for university management to improve the timely graduation ratio.
References
M. Y. L. Ijlal, A. Setiawan, and D. L. Fithri, “Prediksi Ketereratan Karier Lulusan berdasarkan Aspek Akademik dan Non-Akademik berbasis Machine Learning,” Sist. J. Sist. Inf., vol. 14, no. 4, pp. 2540–9719, 2025, [Online]. Available: http://sistemasi.ftik.unisi.ac.id.
Q. Hai and C. Wang, “Optimizing Student Performance Prediction: A Data Mining Approach with MLPC Model and Metaheuristic Algorithm,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 4, pp. 55–71, 2024, doi: 10.14569/IJACSA.2024.0150407.
Z. L. Aripin, A. Rahmatulloh, and E. Haerani, “Smart Payment Predictions: Evaluating Naive Bayes, XGBoost, and Decision Tree Models for Timely Tuition Fees,” Int. J. Informatics Vis., vol. 10, no. 1, pp. 27–32, 2026, doi: 10.62527/joiv.10.1.3717.
E. F. Wati, E. Sunita Perangin-Angin, and A. P. Sari, “Improved Naive Bayes Algorithm with Particle Swarm Optimization to Predict Student Graduation,” Int. J. Inf. Syst. Technol. Akreditasi, vol. 7, no. 6, pp. 386–391, 2024.
K. J. Atmaja, I. P. Y. Indrawan, I. M. Dwi, P. Asana, and I. K. Wawan, “Journal of Computer Networks , Architecture and High Performance Computing Naïve Bayes-based Student Graduation Prediction Model : Effectiveness and Implementation to Improve Timely Graduation,” J. Comput. Networks, Archit. High Perform. Comput., vol. 6, no. 3, pp. 1442–1450, 2024.
W. Shafqat, S. Malik, K. T. Lee, and D. H. Kim, “Pso based optimized ensemble learning and feature selection approach for efficient energy forecast,” Electron., vol. 10, no. 18, 2021, doi: 10.3390/electronics10182188.
L. Santoso and Priyadi, “Comparative Study of Feature Engineering Techniques for Predictive Data Analytics,” J. Technol. Informatics Eng., vol. 3, no. 2, pp. 417–435, 2024, doi: 10.51903/jtie.v3i2.225.
F. Tatimu, V. R. Palilingan, and I. Rianto, “Analisis Klasifikasi Kelulusan Mahasiswa menggunakan Algoritma K-Nearest Neighbor di Fakultas Teknik Universitas Negeri Manado,” J. Educ. Method Technol., vol. 3, no. 1, pp. 117–123, 2025.
A. Rahman, D. Mahdiana, and A. Fauzi, “Predicting Student On-Time Graduation Using Particle Swarm Optimization and Random Forest Algorithms,” Indones. J. Artif. Intell. Data Min., vol. 8, no. 1, p. 161, 2025, doi: 10.24014/ijaidm.v8i1.33577.
R. D. Deleña et al., “Predicting student retention: A comparative study of machine learning approach utilizing sociodemographic and academic factors,” Syst. Soft Comput., vol. 7, no. July, 2025, doi: 10.1016/j.sasc.2025.200352.
A. Nowakowski, L. Strak, and W. Wieczorek, “MAB-optimized binary PSO-based feature selection for enhanced classification performance,” Procedia Comput. Sci., vol. 225, pp. 4264–4273, 2023, doi: 10.1016/j.procs.2023.10.423.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Rudi Hermawan, Muhammad Iqbal
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
International Conference On Islamic Community Studies, Education and Science, its website, and the articles published therein are licensed under a 
