Performance analysis of CNN-KNN co-learning model for adaptive student learning evaluation in higher education settings
Yuan Kang
City University Malaysia/Sanya City Vocational College
M. KazemChamran
Faculty of Information Technology, City University Malaysia
DOI: https://doi.org/10.59429/bam.v8i3.15438
Keywords: adaptive evaluation; educational data mining; CNN-KNN; learning analytics; higher education management; student success
Abstract
This study evaluates a convolutional neural network-k-nearest neighbors (CNN-KNN) co-learning model for adaptive student learning evaluation in higher education. A one-dimensional CNN learns a latent representation, while distance-weighted KNN corrects low-confidence cases through a validation-selected gate. Experiments use the public Predict Students' Dropout and Academic Success dataset with 4,424 student records and 36 demographic, socioeconomic, macroeconomic, and academic variables. Three evidence stages are considered: Enrollment, end of Semester 1, and end of Semester 2. Across three stratified splits, the full-stage CNN-KNN achieved 0.740 ± 0.023 accuracy and 0.691 ± 0.017 macro-F1. Accuracy was slightly above standalone CNN (0.737) and clearly above raw KNN (0.691), although Random Forest remained strongest (0.769 accuracy; 0.708 macro-F1). Accuracy increased from 0.577 at enrollment to 0.721 after Semester 1 and 0.740 after Semester 2. The hybrid is therefore better viewed as a selective, stability-oriented decision-support layer than as a universally superior classifier, while the staged design supports better-timed academic advising and student-support allocation.
References
[1] Albreiki, B., Zaki, N., & Alashwal, H. (2021). A Systematic Literature Review of Student' Performance Prediction Using Machine Learning Techniques. Education Sciences, 11(9), 552. https://doi.org/10.3390/educsci11090552.
[2] Yağcı, M. (2022). Educational data mining: prediction of students' academic performance using machine learning algorithms. Smart Learning Environments, 9, Article 11. https://doi.org/10.1186/s40561-022-00192-z.
[3] Alhothali, A., Albsisi, M., Assalahi, H., & Aldosemani, T. (2022). Predicting Student Outcomes in Online Courses Using Machine Learning Techniques: A Review. Sustainability , 14(10), 6199. https://doi.org/10.3390/su14106199.
[4] Realinho, V., Machado, J., Baptista, L., & Martins, M. V. (2022). Predicting Student Dropout and Academic Success. Data , 7(11), 146. https://doi.org/10.3390/data7110146.
[5] Liao, C.-H., & Wu, J.-Y. (2022). Deploying multimodal learning analytics models to explore the impact of digital distraction and peer learning on student performance. Computers & Education , 190, 104599. https://doi.org/10.1016/j.compedu.2022.104599.
[6] Ouyang, F., Wu, M., Zheng, L., Zhang, L., & Jiao, P. (2023). Integration of artificial intelligence performance prediction and learning analytics to improve student learning in online engineering course. International Journal of Educational Technology in Higher Education , 20, Article 4. https://doi.org/10.1186/s41239-022-00372-4.
[7] Holicza, B., & Kiss, A. (2023). Predicting and Comparing Students' Online and Offline Academic Performance Using Machine Learning Algorithms. Behavioral Sciences, 13(4), 289. https://doi.org/10.3390/bs13040289.
[8] Xue, H., & Niu, Y. (2023). Multi-Output Based Hybrid Integrated Models for Student Performance Prediction. Applied Sciences, 13(9), 5384. https://doi.org/10.3390/app13095384.
[9] Smadi, A., Al-Qerem, A., Nabot, A., Jebreen, I., Aldweesh, A., Alauthman, M., Abaker, A. M., Al Zuobi, O. R., & Alzghoul, M. B. (2023). Unlocking the Potential of Competency Exam Data with Machine Learning: Improving Higher Education Evaluation. Sustainability , 15(6), 5267. https://doi.org/10.3390/su15065267.
[10] Christou, V., Tsoulos, I. G., Loupas, V., Tzallas, A. T., Gogos, C., Karvelis, P. S., Antoniadis, N., Glavas, E., & Giannakeas, N. (2023). Performance and early drop prediction for higher education students using machine learning. Expert Systems with Applications, 225, 120079. https://doi.org/10.1016/j.eswa.2023.120079.
[11] López-García, A., Blasco-Blasco, O., Liern-García, M., & Parada-Rico, S. E. (2023). Early detection of students' failure using Machine Learning techniques. Operations Research Perspectives, 11, 100292. https://doi.org/10.1016/j.orp.2023.100292.
[12] Borna, M.-R., Saadat, H., Hojjati, A. T., & Akbari, E. (2024). Analyzing click data with AI: implications for student performance prediction and learning assessment. Frontiers in Education , 9, 1421479. https://doi.org/10.3389/feduc.2024.1421479.
[13] Lu, J., Liu, Y., Liu, S., Yan, Z., Zhao, X., Zhang, Y., Yang, C., Zhang, H., Su, W., & Zhao, P. (2024). Machine learning analysis of factors affecting college students' academic performance. Frontiers in Psychology , 15, 1447825. https://doi.org/10.3389/fpsyg.2024.1447825.
[14] Turkmenbayev, A., Abdykerimova, E., Nurgozhayev, S., Karabassova, G., & Baigozhanova, D. (2025). The application of machine learning in predicting student performance in university engineering programs: a rapid review. Frontiers in Education , 10, 1562586. https://doi.org/10.3389/feduc.2025.1562586.
[15] Zou, W., Zhong, W., Du, J., & Yuan, L. (2025). Prediction of Student Academic Performance Utilizing a Multi-Model Fusion Approach in the Realm of Machine Learning. Applied Sciences, 15(7), 3550. https://doi.org/10.3390/app15073550.
[16] Realinho, V., Vieira Martins, M., Machado, J., & Baptista, L. (2021). Predict Students' Dropout and Academic Success [Dataset]. UCI Machine Learning Repository . https://doi.org/10.24432/C5MC89.