A Hybrid Machine Learning Approach in Educational Data Mining for Academic Risk Classification

DOI

10.2991/978-94-6239-805-4_32How to use a DOI?

Keywords

Academic; Classification; EDM; Hybrid Machine Learning; KNN

Abstract

Higher education institutions currently face major challenges in managing increasingly complex and diverse student academic data. The available data encompasses exam scores, Grade Point Average (GPA), attendance, and learning activities on e-learning platforms. If analyzed correctly, this data can serve as a vital foundation for detecting students at risk of academic failure. However, traditional methods are often less than optimal when dealing with data heterogeneity. K-Nearest Neighbor (KNN) is known to be effective in proximity-based classification, but it has limitations when confronting complex data distributions. On the other hand, K-means clustering can group students based on similar characteristics, yet it does not provide a clear final classification. Consequently, there is a growing need to develop a hybrid approach that combines the strengths of both KNN and K-means, allowing the academic risk classification process to be carried out more accurately and adaptively. This study utilizes an Educational Data Mining (EDM) approach with a hybrid KNN + K-means model. The research stages begin with the collection of student academic data, including exam scores, GPA, attendance, and learning activities. This data is then processed through K-means clustering to discover patterns and groups of students with similar characteristics. The clustering results are subsequently used as the basis for KNN classification, which determines risk categories based on proximity to labeled student data. The resulting model will be evaluated using accuracy, precision, recall, and F1-score metrics to ensure the reliability of the outcomes.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Made Pasek Agus Ariawan
AU  - Ni Putu Eka Apriyanthi
AU  - Ida Bagus Adisimakrisna
PY  - 2026
DA  - 2026/10/08
TI  - A Hybrid Machine Learning Approach in Educational Data Mining for Academic Risk Classification
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2026 (ICOSTAS-EAS 2026)
PB  - Atlantis Press
SP  - 303
EP  - 313
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-805-4_32
DO  - 10.2991/978-94-6239-805-4_32
ID  - Ariawan2026
ER  -