Volume 13, Issue 8 (August 2026), Pages: 44-53

----------------------------------------------

 Original Research Paper

A knowledge-structured and interpretable machine learning framework for knowledge tracing and learning outcomes

 Author(s): 

Bagabold Gendensuren, Byambasuren Ivanov *, Munkhtsetseg Namsraidorj, Enkhtuul Bukhsuren

 Affiliation(s):

Department of Information and Computer Sciences, School of Information Technology and Electronics, National University of Mongolia, Ulaanbaatar, Mongolia

 Full text

    Full Text - PDF

 * Corresponding Author. 

   Corresponding author's ORCID profile:  https://orcid.org/0000-0001-5236-7857

 Digital Object Identifier (DOI)

 
https://doi.org/10.21833/ijaas.2026.08.005

 Abstract

Knowledge Tracing (KT) models are widely used to estimate learners’ knowledge states. Recent approaches often rely on deep neural architectures, which can be difficult to interpret, computationally expensive, and challenging to deploy in real-world educational settings. In addition, explicitly modeling relationships between topics remains a key challenge. This study proposes a knowledge-structured framework that automatically identifies latent relationships between topics from real learning data and integrates them with machine learning–based prediction. Topic similarity is estimated using cosine similarity to construct a knowledge graph, and learners’ knowledge states are updated through a graph-based propagation process. This approach enables related topics to influence each other, providing a more structured view of learning dynamics. Experimental results show that the proposed method produces more stable and consistent knowledge estimates compared with approaches based solely on raw performance data. The model achieves a Recall of 0.92, an AUC of 0.61, and an RMSE of 0.55, indicating strong sensitivity to learning risk while maintaining stable predictions.

 © 2026 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords

Educational data mining, Graph diffusion, Knowledge graph, Knowledge tracing, Machine learning

 Article history

Received 5 March 2026, Received in revised form 17 July 2026, Accepted 9 August 2026

 Acknowledgment

No Acknowledgment. 

 Compliance with ethical standards

 Citation:

Gendensuren B, Ivanov B, Namsraidorj M, and Bukhsuren E (2026). A knowledge-structured and interpretable machine learning framework for knowledge tracing and learning outcomes. International Journal of Advanced and Applied Sciences, 13(8): 44-53

  Permanent Link to this page

---------------------------------------------- 

 References (17)

1. Baker RS and Inventado PS (2014). Educational data mining and learning analytics. In: Larusson JA and White B (Eds.), Learning analytics: From research to practice: 61–75. Springer, New York, USA. https://doi.org/10.1007/978-1-4614-3305-7_4   [Google Scholar] PMCid:PMC4355053
2. Corbett AT and Anderson JR (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-adapted Interaction, 4: 253-278. https://doi.org/10.1007/BF01099821   [Google Scholar]
3. Cui C, Yao Y, Zhang C, Ma H, Ma Y, Ren Z, Zhang C, and Ko J (2024). DGEKT: A dual graph ensemble learning method for knowledge tracing. ACM Transactions on Information Systems, 42(3): 78. https://doi.org/10.1145/3638350   [Google Scholar]
4. Fawcett T (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8): 861-874. https://doi.org/10.1016/j.patrec.2005.10.010   [Google Scholar]
5. Gantulga B, Munkhtsetseg N, Garmaa D, and Batbayar S (2020). Using five principles of object-oriented design in the transmission network management information. In: Pan JS, Li J, Tsai PW, and Jain L (Eds.), Advances in intelligent information hiding and multimedia signal processing: 325–333. Springer, Singapore, Singapore. https://doi.org/10.1007/978-981-13-9714-1_36   [Google Scholar]
6. Liu M, Shao P, Zhang K (2021). Graph-based exercise- and knowledge-aware learning network for student performance prediction. In: Fang L, Chen Y, Zhai G, Wang J, Wang R, and Dong W (Eds.), Artificial Intelligence: First CAAI International Conference, CICAI 2021, Hangzhou, China, June 5–6, 2021, Proceedings, Part I 1: 27–38. Springer, Cham, Switzerland. https://doi.org/10.1007/978-3-030-93046-2_3   [Google Scholar]
7. Mikolov T, Chen K, Corrado G, and Dean J (2013). Efficient estimation of word representations in vector space. Arxiv Preprint Arxiv:1301.3781. https://doi.org/10.48550/arXiv.1301.3781   [Google Scholar]
8. Nakagawa H, Iwasawa Y, and Matsuo Y (2019). Graph-based knowledge tracing: Modeling student proficiency using graph neural network. In the IEEE/WIC/ACM International Conference on Web Intelligence, ACM, Thessaloniki, Greece: 156-163. https://doi.org/10.1145/3350546.3352513   [Google Scholar] PMid:31029866
9. Namsraidorj M, Namsraidorj B, and Enkhtur A (2025). Ontology-based recommendation system using GitHub Classroom and Bookwidget. TEM Journal, 14(1): 861. https://doi.org/10.18421/TEM141-76   [Google Scholar]
10. Pavlik PI, Cen H, and Koedinger KR (2009). Performance factors analysis: A new alternative to knowledge tracing. In the Proceedings of the 14th International Conference on Artificial Intelligence in Education, IOS Press, Amsterdam, The Netherlands: 531–538. https://doi.org/10.3233/978-1-60750-028-5-531   [Google Scholar]
11. Piech C, Bassen J, Huang J, Ganguli S, Sahami M, Guibas LJ, and Sohl-Dickstein J (2015). Deep knowledge tracing. In the Proceedings of the Advances in Neural Information Processing Systems, Montreal, Canada: 505–513.   [Google Scholar]
12. Tong S, Liu Q, Huang W, Hunag Z, Chen E, Liu C, Ma H, and Wang S (2020). Structure-based knowledge tracing: An influence propagation view. In the IEEE International Conference on Data Mining (ICDM), IEEE, Sorrento, Italy: 541-550. https://doi.org/10.1109/ICDM50108.2020.00063   [Google Scholar]
13. Veličković P, Cucurull G, Casanova A, Romero A, Lio P, and Bengio Y (2017). Graph attention networks. ArXiv Preprint ArXiv:1710.10903. https://doi.org/10.48550/arXiv.1710.10903   [Google Scholar]
14. Wang J and Zhang L (2021). Discriminant mutual information for text feature selection. In: Jensen CS et al. (Eds.), Database systems for advanced applications: 136–151. Springer, Cham, Switzerland. https://doi.org/10.1007/978-3-030-73197-7_9   [Google Scholar]
15. Yang Y, Shen J, Qu Y, Liu Y, Wang K, Zhu Y, Zhang W, and Yu Y (2021). GIKT: A graph-based interaction model for knowledge tracing. In: Hutter F, Kersting K, Lijffijt J, and Valera I (Eds.), Machine learning and knowledge discovery in databases: 299–315. Springer, Cham, Switzerland. https://doi.org/10.1007/978-3-030-67658-2_18   [Google Scholar]
16. Yeung CK and Yeung DY (2018). Addressing two problems in deep knowledge tracing via prediction-consistent regularization. In the Proceedings of the Fifth Annual ACM Conference on Learning at Scale, ACM, London, UK: 1-10. https://doi.org/10.1145/3231644.3231647   [Google Scholar]
17. Yudelson MV, Koedinger KR, and Gordon GJ (2013). Individualized Bayesian knowledge tracing models. In: Lane HC, Yacef K, Mostow J, and Pavlik P (Eds.), Artificial intelligence in education: 171–180. Springer, Berlin, Germany. https://doi.org/10.1007/978-3-642-39112-5_18   [Google Scholar]