A Clustering-Based Framework for Student Academic Performance Analysis and Learning Recommendations
DOI:
https://doi.org/10.29407/zgseqc35Abstract
Student academic data contains valuable information that can be used to support improved learning and decision-making in the field of education. However, conventional academic evaluations often rely on aggregate indicators such as the Cumulative Grade Point Average (GPA), which may not adequately represent the student's learning characteristics and academic needs. This research proposes a clustering-based system to analyze students' academic achievement and generate personalized learning recommendations. The academic records of first-semester students are collected and processed first through feature engineering, by categorizing courses into numerical, practical, and theoretical domains. Three clustering algorithms, namely K-Means, Agglomerative Clustering, and Gaussian Mixture Model (GMM), were evaluated using the Silhouette Score, Davies-Bouldin Index, and Calinski-Harabasz Index. The results showed that K-Means achieved the best performance with a Silhouette Score of 0.4926, the Davies-Bouldin Index of 0.5085, and the Calinski-Harabasz Index of 48.6175. The selected model resulted in three meaningful clusters, representing high, medium, and low-performing students. Based on the results of the grouping and learning profiles, a recommendation framework consisting of nine personalized learning strategies was developed and validated through expert assessment. The proposed system demonstrates the potential of integrating academic performance clustering with learning recommendations to support personalized learning, early academic intervention, and data-driven efforts to improve educational quality.
Keywords:
Educational Data Mining, K-Means Clustering, Academic Performance, Personalized Learning, Learning RecommendationDownloads
References
Allagui, B. (2024). A scaffolding intervention to improve self-efficacy in source-based argumentative writing. Frontiers in Psychology, 15. https://doi.org/10.3389/fpsyg.2024.1454104
Almeqdad, Q. I., Alodat, A. M., Alquraan, M. F., Mohaidat, M. A., & Al-Makhzoomy, A. K. (2023). The effectiveness of universal design for learning: A systematic review of the literature and meta-analysis. Cogent Education, 10(1). https://doi.org/10.1080/2331186X.2023.2218191
Azzahra, C., & Sriani. (2025). Clustering of High School Students Academic Scores Using the K-Means Algorithm. Journal of Information Systems and Informatics, 7(1), 572–586. https://doi.org/10.51519/journalisi.v7i1.1029
Betts, A., Thai, K.-P., & Gunderia, S. (2021). Personalized Mastery Learning Ecosystems: Using Bloom’s Four Objects of Change to Drive Learning in Adaptive Instructional Systems (pp. 29–52). https://doi.org/10.1007/978-3-030-77857-6_3
Chen, T., Zhao, Y.-J., Huang, F.-Q., Liu, Q., Li, Y., Alolga, R. N., Zhang, L., & Ma, G. (2024). The effect of problem-based learning on improving problem-solving, self-directed learning, and critical thinking ability for the pharmacy students: A randomized controlled trial and meta-analysis. PLOS ONE, 19(12), e0314017. https://doi.org/10.1371/journal.pone.0314017
Cheng, Y., Guan, R., Li, T., Raković, M., Li, X., Fan, Y., Jin, F., Tsai, Y.-S., Gašević, D., & Swiecki, Z. (2025). Self-regulated Learning Processes in Secondary Education: A Network Analysis of Trace-based Measures. Proceedings of the 15th International Learning Analytics and Knowledge Conference, 260–271. https://doi.org/10.1145/3706468.3706502
Danu, R., Putra, K., Palupi, K. S., Wakhidah, N., Informasi, J. S., & Akademik, N. (2025). Pengelompokkan Data Nilai Mahasiswa Menggunakan Metode K-Means. Jurnal Algoritme, 6(1), 88–99. https://doi.org/10.35957/algoritme.v6i1.11313
Devi, M. K. K., & Thendral, M. S. (2023). Using Kolb’s Experiential Learning Theory to Improve Student Learning in Theory Course. Journal of Engineering Education Transformations, 37(1), 70–81. https://doi.org/10.16920/jeet/2023/v37i1/23133
Dewi, F. P., Aryni, P. S., & Umaidah, Y. (2022). Implementasi Algoritma K-Means Clustering Seleksi Siswa Berprestasi Berdasarkan Keaktifan dalam Proses Pembelajaran. JISKA (Jurnal Informatika Sunan Kalijaga), 7(2), 111–121.
Dinata, R. K., Novriando, H., Hasdyna, N., & Retno, S. (2020). Reduksi Atribut Menggunakan Information Gain untuk Optimasi Cluster Algoritma K-Means. JEPIN ((Jurnal Edukasi Dan Penelitian Informatika)), 6(1), 48–53.
Hakim, H. T., Usino, W., Informasi, S., Informasi, F. T., Luhur, U. B., Selatan, J., & Clustering, A. (2024). Penerapan Algoritma Agglomerative Clustering Untuk Mengelompokkan Provinsi Di Indonesia Berdasarkan Indikator Pendidikan Application Of Agglomerative Clustering Algorithm To Group Provinces In Indonesia Based On. Bit (Fakultas Teknologi Informasi Universitas Budi Luhur), 21(2), 153–160.
Kinjal, Parida, S. M., Suthar, J., & Pande, S. D. (2024). Predicting Academic Success : A Comparative Study of Machine Learning and Clustering-Based Subject Recommendation Models. EAI Endorsed Transactions on Internet on Things Research, 10, 1–7. https://doi.org/10.4108/eetiot.5378
Kolb, A. Y., & Kolb, D. A. (2022). Experiential Learning Theory as a Guide for Experiential Educators in Higher Education. Experiential Learning and Teaching in Higher Education, 1(1), 38. https://doi.org/10.46787/elthe.v1i1.3362
Latief, M. A., Nabila, L. R., Miftakhurrahman, W., Ma’rufatullah, S., & Tantyoko, H. (2024). Handling Imbalance Data using Hybrid Sampling SMOTE-ENN in Lung Cancer Classification. International Journal of Engineering and Computer Science Applications (IJECSA), 3(1), 11–18. https://doi.org/10.30812/ijecsa.v3i1.3758
Li, S., & Li, D. (2025). RESEARCH ON PERSONALIZED LEARNING RECOMMENDATION SYSTEM BASED ON MACHINE LEARNING ALGORITHM. Scalable Computing: Practice and Experience, 26, 432–440. https://doi.org/10.12694/scpe.v26i1.3844
Maguate, G. S., Odango, J. S., Cruz, J. N. D. Dela, Cornel, M. A., M., A. A., & Uy, F. T. (2024). Analyzing Student Performance : A Clustering Approach for Academic Intervention. INTERNATIONAL MULTIDISCIPLINARY JOURNAL OF RESEARCH FOR INNOVATION, SUSTAINABILITY, AND EXCELLENCE (IMJRISE), (2021), 941–946.
Makawana, M., & Mehta, R. G. (2023). Discovering Search Space Using M-distance Clustering of Semantic Relatedness Based Weighted Network for the Content-based Recommender System. Journal of Scientometric Research, 12(2), 243–253.
Meng, N., Mat Deli, M., & Abdul Rauf, U. A. (2025). Educational Technology and AI: Bridging Cognitive Load and Learner Engagement for Effective Learning. Sage Open, 15(4). https://doi.org/10.1177/21582440251395930
Moriña, A., Carballo, R., & Doménech, A. (2025). Transforming higher education: a systematic review of faculty training in UDL and its benefits. Teaching in Higher Education, 30(7), 1722–1739. https://doi.org/10.1080/13562517.2025.2465994
Ouassif, K., Ziani, B., & Herrera-tapia, J. (2025). Empowering Education : Leveraging Clustering and Recommendations for Enhanced Student Insights. Education Sciences, 1–14.
Ouwehand, K., Lespiau, F., Tricot, A., & Paas, F. (2025). Cognitive Load Theory: Emerging Trends and Innovations. Education Sciences, 15(4), 458. https://doi.org/10.3390/educsci15040458
Rizki, I. A., Sunarti, T., & Salsabila, N. F. (2024). A case study of how digital competencies affect Pre- Service Physics Teachers ’ Professional growth : Realizing SDG 4. E3S Web of Conferences, 04007, 1–10.
Schunk, D. H., & Zimmerman, B. J. (2022). Self-regulation of Learning and Performance. Routledge. https://doi.org/10.4324/9780203763353
Sharif, M. S., Tamang, M. T., Mani, D., & Elmedany, W. (2024). Application of Clustering Algorithms to enhance Personalized Learning through Recommendation Model. International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT). https://doi.org/10.1109/3ict64318.2024.10824599
Stanny, C. J. (2016). Reevaluating bloom’s taxonomy: What measurable verbs can and cannot say about student learning. Education Sciences, 6(4). https://doi.org/10.3390/educsci6040037
Suhana, R., Mahmudy, W. F., & Budi, A. S. (2022). Fish Image Classification using Transfer Learning Method withAdaptive Learning Rate Fish Image Classification using Transfer Learning Method with Adaptive Learning Rate. Knowledge Engineering and Data Science, 5(1).
Syakur, M. A., Khotimah, B. K., Rochman, E. M. S., & Satoto, B. D. (2018). Integration k-means clustering method and elbow method for identification of the best customer profile cluster. IOP Conference Series: Materials Science and Engineering, 336(1), 12017.
Ullah, A., Mohmand, M. I., Hussain, H., Johar, S., & Khan, I. (2023). Customer Analysis Using Machine Learning-Based. Journal Sensors. https://doi.org/https://doi.org/10.3390/s23063180
Utami, I. Q., Hwang, W., & Ningrum, R. A. (2024). Student ’ s Behavior Clustering based on Ubiquitous Learning Log Data using Unsupervised Machine Learning. Journal of Advanced Technology and Multidiscipline (JATM), 03(01), 13–20.
Villegas-ch, W., García-ortiz, J., & Sánchez-viteri, S. (2024). Personalization of Learning : Machine Learning Models for Adapting Educational Content to Individual Learning Styles. 12(August). https://doi.org/10.1109/ACCESS.2024.3452592
Vrbanović Lisac, D., Radanović, I., & Šimić Šašić, S. (2025). Enhancing higher order thinking skills to improve understanding of biological content: A quasi‐experimental study. Natural Sciences Education, 54(2). https://doi.org/10.1002/nse2.70023
Wilson, L. O. (2012). Anderson and Krathwohl Bloom’s Taxonomy Revised Understanding the New Version of Bloom’s Taxonomy.
Zamakhsyari, F., & Fatwanto, A. (2025). Language model optimization for mental health question answering application. International Journal of Electrical and Computer Engineering (IJECE), 15(5), 4829–4836. https://doi.org/10.11591/ijece.v15i5.pp4829-4836
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fardan Zamakhsyari, Nadhira Fasya Salsabila, Rizka Suhana, Sean Ryan Al Dzikri (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
