Machine Learning Based Early Warning Model for Delayed Student Graduation: A Sixth-Semester Prediction Approach
Keywords:
delayed graduation, education data mining, stratified five-fold cross-validation, tuned random forest, tuned support vectorAbstract
Delayed student graduation is a critical issue in higher education because it affects academic planning, student support, and institutional performance evaluation. This study develops a leakage controlled machine learning framework for early identification of students at risk of delayed graduation, using academic records available through the sixth semester. A dataset of 564 students was used, with graduation status defined as on-time for students graduating in the eighth semester or earlier and delayed for those graduating after the eighth semester. To prevent temporal data leakage, post-outcome variables were excluded from the predictor set. Five supervised learning algorithms were evaluated: Decision Tree, Support Vector Machine, Random Forest, Naïve Bayes, and K-Nearest Neighbor. Preprocessing was performed using one-hot encoding and standardization within a pipeline, and model performance was assessed using stratified five-fold cross-validation. The tuned Random Forest achieved the most balanced performance, with 0.956 accuracy, 0.861 delayed-class precision, 0.805 delayed-class recall, 0.832 delayed-class F1-score, and 0.977 ROC-AUC. The tuned SVM with a threshold of 0.30 achieved higher delayed-class recall (0.857) and ROC-AUC (0.980). Feature-importance analysis indicated that fourth and fifth semester GPAs were the strongest predictors. These findings show that machine learning can support early academic intervention and data driven decision making in higher education.References
[1] S. Shilbayeh and A. Abonamah, “Predicting student enrolments and attrition patterns in higher educational institutions using machine learning,” Int. Arab J. Inf. Technol., vol. 18, no. 4, pp. 562–567, 2021, doi: 10.34028/18/4/8.
[2] K. Fahd, Kiran; Miah, Shah Jahan; Ahmed, “Predicting student performance in a blended learning environment using learning management system interaction data,” Appl. Comput. Informatics, 2021, doi: 10.1108/ACI-06-2021-0150.
[3] C. M. Profiroiu, P. S. Angheluță, P. C. Vasilache, and C. Dima, “The Level of Education of Graduates in Romania in the Context of Globalization,” SHS Web Conf., vol. 92, p. 07055, 2021, doi: 10.1051/shsconf/20219207055.
[4] I. H. Sarker, “Machine Learning: Algorithms, Real-World Applications and Research Directions,” SN Comput. Sci., vol. 2, no. 3, pp. 1–21, 2021, doi: 10.1007/s42979-021-00592-x.
[5] J. P. Bharadiya, “The role of machine learning in transforming business intelligence,” Int. J. Comput. Artif. Intell., vol. 4, no. 1, pp. 16–24, 2023, doi: 10.33545/27076571.2023.v4.i1a.60.
[6] N. A. M. Samsudin, S. M. Shaharudin, N. A. F. Sulaiman, S. Ismail, N. S. Mohamed, and N. H. M. Husin, “Prediction of Student‘s Academic Performance during Online Learning Based on Regression in Support Vector Machine,” Int. J. Inf. Educ. Technol., vol. 12, no. 12, pp. 1431–1435, 2022, doi: 10.18178/ijiet.2022.12.12.1768.
[7] T. Handhayani and L. Hiryanto, “Predicting and Analyzing the Students’ Length of Study-Time Using Support Vector Machine,” vol. 8, no. 2, pp. 107–114, 2017, doi: 10.21512/comtech.v8i2.3756.
[8] M. R. P. Putra and E. Utami, “A Blending Ensemble Approach to Predicting Student Dropout in Massive Open Online Courses (MOOCs),” JUITA J. Inform., vol. 13, no. 1, pp. 11–18, 2025, doi: 10.30595/juita.v13i1.24061.
[9] H. Alhakami, T. Alsubait, and A. Aljarallah, “Data mining for student advising,” Int. J. Adv. Comput. Sci. Appl., vol. 11, no. 3, pp. 526–532, 2020, doi: 10.14569/ijacsa.2020.0110367.
[10] N. S. Sani, A. F. M. Nafuri, Z. A. Othman, M. Z. A. Nazri, and K. N. Mohamad, “Drop-Out Prediction in Higher Education Among B40 Students,” Int. J. Adv. Comput. Sci. Appl., vol. 11, no. 11, pp. 550–559, 2020, doi: 10.14569/IJACSA.2020.0111169.
[11] A. S. Hoffait and M. Schyns, “Early detection of university students with potential difficulties,” Decis. Support Syst., vol. 101, pp. 1–11, 2017, doi: 10.1016/j.dss.2017.05.003.
[12] A. Ritesh, A. Jadhav, and S. Dukhan, “Forecasting Learner Attrition for Student Success at a South African University,” ACM Int. Conf. Proceeding Ser., pp. 19–28, 2020, doi: 10.1145/3410886.3410973.
[13] A. F. Gkontzis, “A predictive analytics framework as a countermeasure for attrition of students,” Interact. Learn. Environ., vol. 30, no. 6, pp. 1028–1043, 2022, doi: 10.1080/10494820.2019.1709209.
[14] S. Huang and J. Wei, “Student Performance Prediction in Mathematics Course Based on the Random Forest and Simulated Annealing,” Sci. Program., vol. 2022, 2022, doi: 10.1155/2022/9340434.
[15] J. Alvarado-Uribe, “Student Dataset from Tecnologico de Monterrey in Mexico to Predict Dropout in Higher Education,” Data, vol. 7, no. 9, 2022, doi: 10.3390/data7090119.
[16] J. K. Hoyos and G. Daza, “Predictive Model to Identify College Students with High Dropout Rates,” Rev. Electron. Investig. Educ., vol. 25, no. 13, pp. 1–10, 2023, doi: 10.24320/redie.2023.25.e13.5398.
[17] L. Kemper, G. Vorhoff, and B. U. Wigger, “Predicting student dropout: A machine learning approach,” Eur. J. High. Educ., vol. 10, no. 1, pp. 28–47, 2020, doi: 10.1080/21568235.2020.1718520.
[18] A. R. Anwari and S. Sukirman, “Recommendation system to Select a Major of Vocational School Using Decision Tree,” J. Tek. Inform., vol. 5, no. 2, pp. 589–598, Apr. 2024, doi: 10.52436/1.jutif.2024.5.2.1327.
[19] M. Kumar, V. Bhardwaj, D. Thakral, A. Rashid, and M. T. Ben Othman, “Ensemble Learning Based Model for Student’s Academic Performance Prediction Using Algorithms,” Ing. des Syst. d’Information, vol. 29, no. 5, pp. 1925–1935, 2024, doi: 10.18280/isi.290524.
[20] J. Berens, K. Schneider, S. Gortz, S. Oster, and J. Burgoff, "Early Detection of Students at Risk - Predicting Student Dropouts Using Administrative Student Data fromm German Universities and Machine Learning Methods," J. Educ. Data Min., vol. 11, no. 3, pp. 1–41, 2019, doi: 10.5281/zenodo.3594771.
[21] V. Plotnikova, M. Dumas, and F. P. Milani, “Applying the CRISP-DM data mining process in the financial services industry: Elicitation of adaptation requirements,” Data Knowl. Eng., vol. 139, p. 102013, 2022, doi: https://doi.org/10.1016/j.datak.2022.102013.
[22] C. Schröer, F. Kruse, and J. M. Gómez, “A systematic literature review on applying CRISP-DM process model,” Procedia Comput. Sci., vol. 181, no. 2019, pp. 526–534, 2021, doi: 10.1016/j.procs.2021.01.199.
[23] M. K. Dahouda and I. Joe, “A Deep-Learned Embedding Technique for Categorical Features Encoding,” IEEE Access, vol. 9, pp. 114381–114391, 2021, doi: 10.1109/ACCESS.2021.3104357.
[24] T. Jo, Machine Learning Foundations: Supervised, Unsupervised, and Advanced Learning, 1st ed. Springer Cham, 2021. doi: 10.1007/978-3-030-65900-4.
[25] V. Matzavela and E. Alepis, “Decision tree learning through a Predictive Model for Student Academic Performance in Intelligent M-Learning environments,” Comput. Educ. Artif. Intell., vol. 2, p. 100035, 2021, doi: 10.1016/j.caeai.2021.100035.
[26] F. Agrusti, G. Bonavolontà, and M. Mezzini, “University dropout prediction through educational data mining techniques: A systematic review,” J. E-Learning Knowl. Soc., vol. 15, no. 3, pp. 161–182, 2019, doi: 10.20368/1971-8829/1135017.
[27] D. A. Otchere, T. O. Arbi Ganat, R. Gholami, and S. Ridha, “Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties: Comparative analysis of ANN and SVM models,” J. Pet. Sci. Eng., vol. 200, no. November 2020, p. 108182, 2021, doi: 10.1016/j.petrol.2020.108182.
[28] M. Nachouki, E. A. Mohamed, R. Mehdi, and M. Abou Naaj, “Student course grade prediction using the random forest algorithm: Analysis of predictors’ importance,” Trends Neurosci. Educ., vol. 33, p. 100214, 2023, doi: https://doi.org/10.1016/j.tine.2023.100214.
[29] T. T. Huynh-Cam, L. S. Chen, and H. Le, “Using decision trees and random forest algorithms to predict and determine factors contributing to first-year university students’ learning performance,” Algorithms, vol. 14, no. 11, 2021, doi: 10.3390/a14110318.
[30] I. B. Mahendra, I. M. G. Sunarya, and I. M. A. Wirawan, “Comparison of Multinomial, Bernoulli, and Gaussian Naïve Bayes for Complaint Classification in Pro Denpasar Application,” JUITA J. Inform., vol. 13, no. 1, pp. 77–86, 2025, doi: 10.30595/juita.v13i1.24828.
[31] J. A Ilemobayo, “Hyperparameter Tuning in Machine Learning: A Comprehensive Review,” J. Eng. Res. Reports, vol. 26, no. 6 SE-Review Article, pp. 388–395, Jun. 2024, doi: 10.9734/jerr/2024/v26i61188.
[32] J. Li, “Area under the ROC Curve has the most consistent evaluation for binary classification,” PLoS One, vol. 19, no. 12 December, 2024, doi: 10.1371/journal.pone.0316019.
[33] A. Abu Saa, M. Al-Emran, and K. Shaalan, Factors Affecting Students’ Performance in Higher Education: A Systematic Review of Predictive Data Mining Techniques, vol. 24, no. 4. Springer Netherlands, 2019. doi: 10.1007/s10758-019-09408-7.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Benny Daniawan, Suwitno Suwitno, Andri Wijaya, Ardiane Rossi Kurniawan Maranto, Junaedi Junaedi
This work is licensed under a Creative Commons Attribution 4.0 International License.
JUITA: Jurnal Informatika is licensed under a Creative Commons Attribution 4.0 International License.
