Machine Learning Pipeline for Educational Prediction and Student Segmentation
DOI:
https://doi.org/10.59261/bustechno.v7i4.820Keywords:
Feature Engineering, Machine Learning, Predictive Modeling, Student SegmentationAbstract
Background: Educational data mining has become increasingly important for understanding student performance and learning patterns; however, challenges in data preprocessing, feature selection, interpretability, and the limited integration of predictive modeling with clustering remain unresolved.
Objective: This study develops an integrated machine-learning workflow that combines feature engineering, predictive modeling, and student segmentation for educational data analysis.
Methods: The analytical dataset contains 343 student records and 87 numeric features after data-type conversion, with Adaptability as the prediction target. The workflow combines data-quality control, feature engineering, ANOVA, mutual information, and recursive feature elimination (RFE) for feature selection; comparative classification; stratified cross-validation; and K-means clustering with principal component analysis (PCA) for student segmentation.
Results: Logistic Regression produced the strongest reported discrimination (Accuracy = 0.9855; Precision = 1.0000; Recall = 0.9697; F1 = 0.9846; MCC = 0.9713; Kappa = 0.9709; AUC = 0.997). AUC values for the remaining models ranged from 0.958 (KNN) to 0.996 (Gradient Boosting). Feature rankings are interpreted as predictive associations rather than causal effects, and clustering provides descriptive student subgroups.
Conclusion: The study provides a traceable, dataset-specific workflow linking preprocessing, feature construction and selection, predictive benchmarking, and descriptive student segmentation. Generalization beyond the supplied dataset requires external validation, and the clustering results should not be interpreted as evidence of intervention effects.
References
Ahmed, N. (2020). Guidelines for deploying ML models in education. International Journal of Artificial Intelligence in Education, 30(3), 407–425.
Y., A., R., F., Mu’az, B., U., H., S., A., A. Y., I., A. I., H., & M. A., B. (2024). Application of Machine Learning in Education: Recent Trends Challenges and Future Perspective. British Journal of Computer, Networking and Information Technology, 7(3). https://doi.org/10.52589/bjcnit-yljqocvp
Brown, L., & Taylor, J. (2020). Ensemble modeling for predictive accuracy. Applied Artificial Intelligence, 34(10), 870–885.
Brown, T., & Green, M. (2020). Feature selection methods for student outcome prediction. International Journal of Machine Learning and Cybernetics, 11, 2347–2360.
Chen, D., & Zhao, Y. (2019). Comparative study of ML models in education. Neural Computing and Applications, 31(10), 6393–6407.
Chen, X., & Hu, Y. (2020). Evaluation metrics for imbalanced educational data. Information Sciences, 512, 1024–1038.
Chen, Y., & Zhang, H. (2019). Outlier detection in student performance data. Expert Systems with Applications, 126, 217–229.
Cho, M., Kim, J., Kim, J., & Park, K. (2024). Integrating Business Analytics in Educational Decision-Making: A Multifaceted Approach to Enhance Learning Outcomes in EFL Contexts. Mathematics, 12(5). https://doi.org/10.3390/math12050620
de la Cruz Huayanay, A., Bazán, J. L., & Russo, C. M. (2025). Performance of evaluation metrics for classification in imbalanced data. Computational Statistics, 40(3), 1447–1473.
Desai, S., Hembade, S. C., Joglekar, S., Mahadik, R. V., Deshmukh, D., & Desai, A. (2026). Predictive Analytics For Student Performance In Digital Media Courses. ShodhKosh: Journal of Visual and Performing Arts, 7(1s). https://doi.org/10.29121/shodhkosh.v7.i1s.2026.6804
Garcia, L., & Adams, T. (2021). Interpretability in machine learning for education. AI in Education, 32(2), 85–101.
Georgiou, G. P. (2026). Machine Learning in Education. In Algorithms (Vol. 19, Number 6). Multidisciplinary Digital Publishing Institute (MDPI). https://doi.org/10.3390/a19060441
Hernandez, A. (2020). Data visualization techniques for educators. Journal of Educational Computing Research, 57(8), 1932–1950.
Hernandez, C. (2019). Data cleaning and preprocessing in education. Education and Information Technologies, 24, 3201–3216.
Johnson, P. (2019). Predictive analytics for student performance. Journal of Learning Analytics, 6(1), 10–25.
Kim, J., & Park, S. (2021). Clustering techniques for student data analytics. Applied Soft Computing, 110, 107643.
Kim, S., & Park, J. (2020). Clustering approaches for student segmentation. Applied Artificial Intelligence, 34(7), 581–598.
Koukaras, P., & Tjortjis, C. (2025). Data Preprocessing and Feature Engineering for Data Mining: Techniques, Tools, and Best Practices. In AI (Switzerland) (Vol. 6, Number 10). https://doi.org/10.3390/ai6100257
Lee, J., & Choi, S. (2020). Feature engineering for student engagement prediction. IEEE Access, 8, 128130–128142.
Lee, K., & Park, H. (2020). Multi-method features selection comparisons. Pattern Recognition Letters, 137, 118–127.
Li, J. (2021). Learning curves and model generalization in student prediction. Applied Soft Computing, 109, 107486.
Lin, H., & Wang, C. (2019). Machine learning applications in predicting academic success. Educational Technology & Society, 22(4), 45–60.
Liu, N., & Wang, H. (2008). Improving predictive accuracy by evolving feature selection for face recognition. IEICE Electronics Express, 5(24). https://doi.org/10.1587/elex.5.1061
Magar, V., Ruikar, D., Bhoite, S., & Mente, R. (2024). Innovative Inter Quartile Range-based Outlier Detection and Removal Technique for Teaching Staff Performance Feedback Analysis. Journal of Engineering Education Transformations, 37(3). https://doi.org/10.16920/jeet/2024/v37i3/24013
Mathibela, M. R., & Maposa, D. (2026). Predictive Modelling of Credit Default Risk Using Machine Learning and Ensemble Techniques. Mathematical and Computational Applications, 31(2). https://doi.org/10.3390/mca31020045
Nguyen, P. (2021a). Data quality management for machine learning in education. IEEE Transactions on Learning Technologies, 14(2), 213–225.
Nguyen, P. (2021b). Data quality management for machine learning in education. IEEE Transactions on Learning Technologies, 14(2), 213–225.
Nguyen, T. (2021). Integrating prediction and clustering in educational analytics. Computers in Human Behavior, 115, 106622.
Patel, M., & Singh, R. (2021). Improving predictive accuracy with feature selection. Education and Information Technologies, 26(4), 4503–4520.
Patel, R. (2021). Feature engineering for academic performance prediction. Expert Systems with Applications, 177, 114902.
Pradini, R. S., Yulianti, Y., & Anshori, M. (2026). Analysis of K-Means Clustering Implementation for New Student Segmentation Based on School of Origin and Study Program. Engineering, MAthematics and Computer Science Journal (EMACS), 8(2), 145–157.
Qin, R., Liu, D., Xu, C., Yan, Z., Tan, Z., Jia, Z., Nassereldine, A., Li, J., Jiang, M., Abbasi, A., Xiong, J., & Shi, Y. (2025). Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices. ACM Transactions on Design Automation of Electronic Systems, 30(5). https://doi.org/10.1145/3736721
Ranjan Banerjee. (2025). Analyzing Student Achievement with Clustering Techniques in Educational Analytics. Panamerican Mathematical Journal, 35(1s). https://doi.org/10.52783/pmj.v35.i4s.6014
Sharifnia, A. M., Kpormegbey, D. E., Thapa, D. K., & Cleary, M. (2026). A Primer of Data Cleaning in Quantitative Research: Handling Missing Values and Outliers. Journal of Advanced Nursing, 82(1). https://doi.org/10.1111/jan.16908
Shrutika Rathore, Rahul Nawkhare, Navin Sharma, Nitin Chaudhary, Saurabh Chakole, & Bhaskar Vishwakrama. (2025). Effective Data Visualization Techniques for Business Decision-Makers. International Research Journal on Advanced Engineering and Management (IRJAEM), 3(05). https://doi.org/10.47392/irjaem.2025.0318
Singh, P., & Verma, R. (2020). Student segmentation using K-means clustering. Educational Data Mining Review, 9(1), 22–35.
Smith, A., & Jones, B. (2019). Preprocessing methods for large educational datasets. Journal of Educational Data Mining, 11(3), 34–50.
Smith, J., & Brown, L. (2020). Machine learning in education: Trends and applications. International Journal of Educational Data Mining, 12(2), 45–60.
Thompson, S. (2020). Handling missing values in educational datasets. IEEE Transactions on Learning Technologies, 13(3), 367–378.
Wang, H., & Liu, S. (2020). Integrated ML pipelines in educational analytics. Computers in Human Behavior, 110, 106396.
Wang, L., Shi, L., Reimers, C., Wang, Y., He, L., Wang, Y., Reichstein, M., & Jiang, S. (2025). A self-supervised deep learning model for enhanced generalization in soil moisture prediction. Journal of Hydrology, 662. https://doi.org/10.1016/j.jhydrol.2025.133974
Wang, L., & Zhou, M. (2019). Multi-method feature selection techniques. Pattern Recognition Letters, 122, 77–85.
Wang, R. (2021). Outlier impact on educational ML models. Expert Systems with Applications, 178, 114974.
Williams, R. (2020). Visual analytics for educational insights. Journal of Learning Analytics, 7(1), 33–47.
Williams, R., & Lee, K. (2021). Feature engineering techniques in educational data. Computers & Education, 165, 104140.
Zhao, W., & Li, P. (2019). Comprehensive machine learning pipelines for education. Journal of Educational Data Science, 4(1), 15–30.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Stanislaus Junanta, Imam Yuadi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International (CC-BY-SA). that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
