Comparative Analysis of Machine Learning Algorithm and Feature Selection on Student Grade Small Datasets
DOI:
https://doi.org/10.31571/ijcmasted.v1i1.1010Keywords:
Comparative, Machine Learning, Feature Selection, Small Dataset, StudentAbstract
Assessment of student academic performance is an important aspect in improving the quality of the learning process in higher education. With the development of Machine Learning (ML) techniques, predictive analysis of student assessment data can be carried out more accurately and efficiently. This research aims to analyze the comparative performance of several ML algorithms and evaluate the effectiveness of various feature selection techniques on student assessment datasets. The dataset used is a limited dataset that contains attributes that represent components of student academic assessment. The research process includes determining cross-validation, applying ML algorithms, applying feature selection techniques, and performance evaluation. The ML algorithms compared are Naïve Bayes, K-Nearest Neighbors (k-NN), Support Vector Machine (SVM), Tree, Random Forest, and AdaBoost. Several feature selection techniques used are Information Gain (IG), Gain Ratio (GR), Gini Dicrease (GD), ReliefF. Evaluation of the performance of the ML algorithm uses the Confusion Matrix in the form of accuracy, precision, recall and F1-score, while the performance evaluation of the feature selection technique uses Spearman Correlation. Experimental results show that the SVM algorithm shows the best performance followed by k-NN. However, based on computing time testing, the Tree algorithm shows the fastest time. Apart from that, the comparison results of feature selection techniques show that Gini Decrease has the best correlation. The findings of this research contribute to selecting a more effective educational data analysis method and can be a reference for developing ML algorithms in student academic evaluation
References
Bashir, S., Khan, Z. S., Khan, F. H., Anjum, A., & Bashir, K. (2019). Improving Heart Disease Prediction Using Feature Selection Approaches. 2019 16th International Bhurban Conference on Applied Sciences and Technology (IBCAST), 619–623. https://doi.org/10.1109/IBCAST.2019.8667106
Boateng, E. Y., Otoo, J., & Abaye, D. A. (2020). Basic Tenets of Classification Algorithms K -Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network : A Review. Journal of Data Analysis and Information Processing, 8(1), 341–357. https://doi.org/10.4236/jdaip.2020.84020
Casteren, W. Van. (2017). The Waterfall Model And The Agile Methodologies : A Comparison By Project Characteristics-Short The Waterfall Model and Agile Methodologies. Academic Competences in the Bachelor, February, 10–13. https://www.researchgate.net/publication/313768860
Jia, K., Yang, Z., Zheng, L., Zhu, Z., & Bi, T. (2021). Spearman Correlation-Based Pilot Protection for Transmission Line Connected to PMSGs and DFIGs. IEEE Transactions on Industrial Informatics, 17(7), 4532–4544. https://doi.org/10.1109/TII.2020.3018499
Korkmaz, C., & Correia, A.-P. (2019). A review of research on machine learning in educational technology. Educational Media International, 56(3), 250–267. https://doi.org/10.1080/09523987.2019.1669875
Ohsaki, M., Wang, P., Matsuda, K., Katagiri, S., Watanabe, H., & Ralescu, A. (2017). Confusion-matrix-based kernel logistic regression for imbalanced data classification. IEEE Transactions on Knowledge and Data Engineering, 29(9), 1806–1819. https://doi.org/10.1109/TKDE.2017.2682249
Popchev, I., & Orozova, D. (2023). Algorithms for Machine Learning with Orange System. International Journal of Online and Biomedical Engineering, 19(4), 109–123. https://doi.org/10.3991/ijoe.v19i04.36897
Sorensen, Lucy C. (2019). “Big Data” in Educational Administration: An Application for Predicting School Dropout Risk. Educational Administration Quarterly, 55(3), 404–446. https://doi.org/10.1177/0013161X18799439
Sulistiani, H., Syarif, A., Muludi, K., & Warsito. (2024). Performance evaluation of feature selections on some ML approaches for diagnosing the narcissistic personality disorder. Bulletin of Electrical Engineering and Informatics, 13(2), 1383–1391. https://doi.org/10.11591/eei.v13i2.6717
Wang, J., Zhou, S., Yi, Y., & Kong, J. (2014). An improved feature selection based on effective range for classification. The Scientific World Journal, 2014. https://doi.org/10.1155/2014/972125
Yan, T., Shen, S.-L., Zhou, A., & Chen, X. (2022). Prediction of geological characteristics from shield operational parameters by integrating grid search and K-fold cross validation into stacking classification algorithm. Journal of Rock Mechanics and Geotechnical Engineering, 14(4), 1292–1303. https://doi.org/https://doi.org/10.1016/j.jrmge.2022.03.002
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Agus Wantoro, Nur Aminudin, Dita Septasari, Ningsiah Ningsiah, Ikna Awaliyani (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All articles published in the Proceeding of IJC-MaSTEd (International Joint Conference on Mathematics, Science, Technology, and Education) are published as open access and are licensed under the Creative Commons Attribution–ShareAlike 4.0 International License (CC BY-SA 4.0).
This license permits anyone to read, download, copy, distribute, adapt, and reuse the published work in any medium or format, including for commercial purposes, provided that proper credit is given to the original author(s) and source, a link to the license is included, and any modifications are clearly indicated. Any derivative works must be distributed under the same license (CC BY-SA 4.0).
Author Rights
Authors retain full copyright of their work. By submitting and publishing in the Proceeding of IJC-MaSTEd, authors grant the publisher a non-exclusive right to publish, distribute, and archive the article as part of the conference proceedings.
Authors are allowed to share, deposit, and reuse their published articles for academic, educational, and research purposes, provided proper attribution is given.
User Rights
Users may freely access and reuse all published content without prior permission, as long as appropriate attribution is provided and the same license terms are maintained.
Third-Party Material
Any third-party material included in an article must be clearly identified and is not covered by the Creative Commons license unless explicitly stated.
By submitting a manuscript to the Proceeding of IJC-MaSTEd, authors confirm that they agree with the open access policy and the license terms stated above.
