Optimizing Small-Data Learning in Elementary Education: An Explainable Restricted Random Forest Approach for Early Warning
Keywords:
Early Warning System, educational data mining, explainable AI, random forest, student performance predictionAbstract
The delayed identification of students at risk of academic underperformance frequently undermines the effectiveness of pedagogical interventions. This limitation arises because most traditional models for predicting student performance depend on exhaustive end-of-semester datasets, engendering a latency issue wherein insights emerge too late for timely remediation. To overcome this, we propose an Explainable Early Warning System that forecasts students' Final Year Mathematics Assessment scores using exclusively mid-semester data: Daily Assessments and Mid-Semester Assessments. By utilizing an augmented dataset of 68 students, hybrid data augmentation to fix class imbalance, and a Restricted Random Forest model to prevent overfitting, our method achieves a strong 92.3% classification accuracy on unseen test data. Remarkably, it achieves 100% Recall for the 'Need Guidance' class, ensuring no at-risk students are overlooked. Furthermore, SHAP analysis reveals that, beyond midterm scores, consistency in specific daily tasks, particularly Daily Assessment Chapter 4 significantly impacts failure risk. In conclusion, combining data augmentation with explainable machine learning transforms predictions into actionable pedagogical insights, empowering teachers to execute precise interventions three months prior to the final exam.References
[1] P. Black and D. Wiliam, Inside the black box: Raising standards through classroom assessment. Granada Learning Assesment, 1998.
[2] J. Hattie, Visible learning: A synthesis of over 800 meta-analyses relating to achievement. Routledge, 2009.
[3] C. A. Tomlinson, The differentiated classroom: Responding to the needs of all learners, 2nd ed. Ascd, 2014.
[4] S. Abouelnour, A. Al Redhaei, M. Azmi Al-Betar, and G. Al-Naymat, “Machine Learning in Higher Education: Predicting and Mitigating Student Dropout,” in 2024 25th International Arab Conference on Information Technology (ACIT), IEEE, Dec. 2024, pp. 1–7. doi: 10.1109/ACIT62805.2024.10877099.
[5] Anjana S and Dr. V. Vijayakumar, “Student Dropout Prediction,” International Journal of Advanced Research in Science, Communication and Technology, pp. 182–192, Apr. 2025, doi: 10.48175/IJARSCT-25225.
[6] H. Nguyen Thi Cam, A. Sarlan, and N. I. Arshad, “A hybrid model integrating recurrent neural networks and the semi-supervised support vector machine for identification of early student dropout risk,” PeerJ Comput. Sci., vol. 10, p. e2572, Nov. 2024, doi: 10.7717/peerj-cs.2572.
[7] Muhammad Ricky Perdana Putra and Ema Utami, “Comparative Analysis of Hybrid Model Performance Using Stacking and Blending Techniques for Student Drop Out Prediction In MOOC,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 8, no. 3, pp. 346–354, Jun. 2024, doi: 10.29207/resti.v8i3.5760.
[8] M. Y. Putra, I. Ayu Lestary, S. Solikin, R. Triharsono, A. Nurul Alfian, and L. Kamila Kulsum, “Hybrid Voting Ensemble of Logistic Regression, Random Forest, KNN, SVM, and XGBoost for Student Drop Out Prediction,” in 2025 Tenth International Conference on Informatics and Computing (ICIC), IEEE, Oct. 2025, pp. 1–6. doi: 10.1109/ICIC68054.2025.11309379.
[9] O. C. Olayemi, O. O. Olasehinde, and O. O. Akinade, “Bias-Aware Machine Learning for Student Dropout Prediction: Balancing Accuracy and Fairness,” Asian Journal of Engineering and Applied Technology, vol. 14, no. 2, pp. 51–57, Dec. 2025, doi: 10.70112/ajeat-2025.14.2.4330.
[10] M. Rebelo Marcolino et al., “Student dropout prediction through machine learning optimization: insights from moodle log data,” Sci. Rep., vol. 15, no. 1, p. 9840, Mar. 2025, doi: 10.1038/s41598-025-93918-1.
[11] N.B. Mahesh Kumar, T. Chithrakumar, T. Thangarasan, J. Dhanasekar, and P. Logamurthy, “AI-Powered Early Detection and Prevention System for Student Dropout Risk,” International Journal of Computational and Experimental Science and Engineering, vol. 11, no. 1, Jan. 2025, doi: 10.22399/ijcesen.839.
[12] F. N. Osman, M. A. Abdul Aziz, and M. N. Taib, “Comparative Evaluation of Feature Selection Algorithms for Predictive Modeling of Academic Performance Outcomes,” in 2024 IEEE 13th International Conference on Engineering Education (ICEED), IEEE, Nov. 2024, pp. 1–6. doi: 10.1109/ICEED62316.2024.10923823.
[13] A. Jain, A. K. Dubey, S. Khan, A. Panwar, M. Alkhatib, and A. M. Alshahrani, “A PSO weighted ensemble framework with SMOTE balancing for student dropout prediction in smart education systems,” Sci. Rep., vol. 15, no. 1, p. 17463, May 2025, doi: 10.1038/s41598-025-97506-1.
[14] M. Pathiranagama, I. Nanayakkara, R. Abeyweera, and T. Halloluwa, “Beyond the Black Box: An Interpretable Machine Learning Approach to Student Dropout Prediction,” in 2025 7th International Conference on Advancements in Computing (ICAC), IEEE, Dec. 2025, pp. 1–6. doi: 10.1109/ICAC69156.2025.11361534.
[15] B. B. Alkan, S. Kuzucuk, N. Alkan, and A. Sinan, “Using machine learning to predict student outcomes for early intervention and formative assessment,” Sci. Rep., vol. 15, no. 1, p. 39797, Nov. 2025, doi: 10.1038/s41598-025-23409-w.
[16] Mst. R. Khatun, M. A. Mim, Md. M. Tasin, and Md. M. Hossain, “A hybrid framework of statistical, machine learning, and explainable AI methods for school dropout prediction,” PLoS One, vol. 20, no. 9, p. e0331917, Sep. 2025, doi: 10.1371/journal.pone.0331917.
[17] M. Yağcı, “Educational data mining: prediction of students’ academic performance using machine learning algorithms,” Smart Learning Environments, vol. 9, no. 1, p. 11, Dec. 2022, doi: 10.1186/s40561-022-00192-z.
[18] R. A. M. Al Hashmi, I. Ozturk, and H. M. Elmehdi, “Early detection of at-risk health sciences students: a machine learning-based predictive study using midterm grades,” BMC Med. Educ., vol. 25, no. 1, p. 1651, Nov. 2025, doi: 10.1186/s12909-025-08192-6.
[19] Faruk Abdulla, “Explainable AI for Students Performance Prediction System,” Int. J. Appl. Math. (Sofia)., vol. 38, no. 12s, pp. 405–427, Dec. 2025, doi: 10.12732/ijam.v38i12s.1389.
[20] E. Ben George, “Explainable AI Methods for Predicting Student Grades and Improving Academic Success,” Journal of Information Systems Engineering and Management, vol. 10, no. 23s, pp. 117–126, Mar. 2025, doi: 10.52783/jisem.v10i23s.3680.
[21] B. Ujkani, D. Minkovska, and N. Hinov, “Course Success Prediction and Early Identification of At-Risk Students Using Explainable Artificial Intelligence,” Electronics (Basel)., vol. 13, no. 21, p. 4157, Oct. 2024, doi: 10.3390/electronics13214157.
[22] S. H. Ali Ijaz, “Explainable AI Framework for Predicting Student Academic Success Through Personality Analysis,” Machine Learning for Human Intelligence, 2025, doi: 10.65492/01/302/2025/29.
[23] R. Tariq, M. G. Orozco-del-Castillo, M. T. Zamir, M. S. Ramírez-Montoya, and T. Wilberforce, “Explainable artificial intelligence for predictive modeling of student stress in higher education,” Sci. Rep., vol. 15, no. 1, p. 38375, Nov. 2025, doi: 10.1038/s41598-025-22171-3.
[24] H. Mastour, T. Dehghani, E. Moradi, and S. Eslami, “Explainable artificial intelligence for predicting medical students’ performance in comprehensive assessments,” Sci. Rep., vol. 15, no. 1, p. 23752, Jul. 2025, doi: 10.1038/s41598-025-07460-1.
[25] A. Alnoman, “Explainable AI for Smart Education: A Case Study on Student Performance Prediction,” in 2025 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), IEEE, Oct. 2025, pp. 1–6. doi: 10.1109/INISTA68122.2025.11249657.
[26] J. Mai, F. Wei, W. He, H. Huang, and H. Zhu, “An Explainable Student Performance Prediction Method Based on Dual-Level Progressive Classification Belief Rule Base,” Electronics (Basel)., vol. 13, no. 22, p. 4358, Nov. 2024, doi: 10.3390/electronics13224358.
[27] S. Sarmini, S. Sunardi, and A. Fadlil, “Evaluating The Effectiveness of Augmentation and Classifier Algorithms for Fraud Detection: Comparing CGAN and SMOTE with Random Forest and XGBoost,” Applied Information System and Management (AISM), vol. 8, no. 2, pp. 221–230, Oct. 2025, doi: 10.15408/492myj05.
[28] R. Bounab, K. Zarour, B. Guelib, and N. Khlifa, “Enhancing Medicare Fraud Detection Through Machine Learning: Addressing Class Imbalance With SMOTE-ENN,” IEEE Access, vol. 12, pp. 54382–54396, 2024, doi: 10.1109/ACCESS.2024.3385781.
[29] F. Gurcan and A. Soylu, “Learning from Imbalanced Data: Integration of Advanced Resampling Techniques and Machine Learning Models for Enhanced Cancer Diagnosis and Prognosis,” Cancers (Basel)., vol. 16, no. 19, p. 3417, Oct. 2024, doi: 10.3390/cancers16193417.
[30] R. Setiawan, E. Nursasongko, A. Syukur, F. Budiman, and D. Kurniadi, “Handling Class Imbalance in Student Success Prediction Using Machine Learning: A Comparison of SMOTE and SMOTETomek,” in 2025 International Conference on Smart Computing, IoT and Machine Learning (SIML), IEEE, Jun. 2025, pp. 1–6. doi: 10.1109/SIML65326.2025.11081128.
[31] M. Nagy and R. Molontay, “Interpretable Dropout Prediction: Towards XAI-Based Personalized Intervention,” Int. J. Artif. Intell. Educ., vol. 34, no. 2, pp. 274–300, Jun. 2024, doi: 10.1007/s40593-023-00331-8.
[32] H. Liu, M. Mao, X. Li, and J. Gao, “Model interpretability on private-safe oriented student dropout prediction,” PLoS One, vol. 20, no. 3, p. e0317726, Mar. 2025, doi: 10.1371/journal.pone.0317726.
[33] M. Mujahid et al., “Data oversampling and imbalanced datasets: an investigation of performance for machine learning and feature engineering,” J. Big Data, vol. 11, no. 1, p. 87, Jun. 2024, doi: 10.1186/s40537-024-00943-4.
[34] M. Kannan, D. Umamaheswari, B. Manimekala, I. P. S. Mary, P. M. Savitha, and J. Rozario, “An enhancement of machine learning model performance in disease prediction with synthetic data generation,” Sci. Rep., vol. 15, no. 1, p. 33482, Sep. 2025, doi: 10.1038/s41598-025-15019-3.
[35] R. A. Ruslan, N. Arbaiy, and P.-C. Lin, “Enhancing Imbalanced Data Augmentation: A Comparative Study of GANified-SMOTE and Latent Factor Integration,” Journal of Informatics and Web Engineering, vol. 4, no. 3, pp. 483–493, Oct. 2025, doi: 10.33093/jiwe.2025.4.3.30.
[36] A. Larasati, S. Surono, A. Thobirin, and D. A. Dewi, “Performance Analysis of Resampling Techniques for Overcoming Data Imbalance in Multiclass Classification,” JUITA: Jurnal Informatika, pp. 57–66, Mar. 2025, doi: 10.30595/juita.v13i1.25270.
[37] S. Fathmah, D. Kartini, F. Abadi, I. Budiman, and M. I. Mazdadi, “Implementation of PPCA Imputation, SMOTE-N Class Balancing in Hepatitis Classification Using Naïve Bayes,” JUITA: Jurnal Informatika, vol. 12, no. 2, p. 169, Nov. 2024, doi: 10.30595/juita.v12i2.21528.
[38] M. Lünich and B. Keller, “Explainable Artificial Intelligence for Academic Performance Prediction. An Experimental Study on the Impact of Accuracy and Simplicity of Decision Trees on Causability and Fairness Perceptions,” in The 2024 ACM Conference on Fairness, Accountability, and Transparency, New York, NY, USA: ACM, Jun. 2024, pp. 1031–1042. doi: 10.1145/3630106.3658953.
[39] S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds., Curran Associates, Inc., 2017. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
[40] L. Antwarg, R. M. Miller, B. Shapira, and L. Rokach, “Explaining anomalies detected by autoencoders using Shapley Additive Explanations,” Expert Syst. Appl., vol. 186, p. 115736, 2021, doi: https://doi.org/10.1016/j.eswa.2021.115736.
[41] T. Tong and Z. Li, “Predicting learning achievement using ensemble learning with result explanation,” PLoS One, vol. 20, no. 1, p. e0312124, Jan. 2025, doi: 10.1371/journal.pone.0312124.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Supriyanto Supriyanto, Ragil Dian Purnama Putri
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.
