Explainable Bayesian Network Recommender for Personalized University Program Selection
DOI:
https://doi.org/10.62411/jcta.12720Keywords:
Bayesian Network, Educational Data Mining, Hill Climbing Structure Learning, Personalized Recommendation, Probabilistic Graphical Model, Recommender System, Sensitivity AnalysisAbstract
In a context where students face increasingly complex academic choices, this work proposes a recommendation system based on Bayesian networks to guide new baccalaureate holders in their university choices. Using a dataset containing variables such as secondary school section, gender, type of school, percentage obtained, age, and first-year honors, we have constructed a probabilistic model capturing the dependencies between these characteristics and the option chosen. The data is collected at the Catholic University of Bukavu, the Official University of Bukavu, and the Higher Institute of Education of Bukavu, preprocessed and then used to learn the structure via the hill-climbing algorithm with the BIC score using R's bnlearn tool. The model enables us to estimate the probability that a candidate will choose a given stream, depending on their profile. The approach has been validated using metrics such as BIC, cross-validation, and bootstrap and offers a good compromise between interpretability and predictive performance. The results highlight the potential of Bayesian networks in constructing explainable recommendation systems in the field of academic guidance. The system produces orientation probability maps for each candidate, which can be used by enrollment service advisers, as well as an ordered list of options relevant to the candidate's profile. With a remarkable performance on a test sample of precision@k=0.85, recall@k=0.61, ndcg=0.8, and Map=0.88, it constitutes an effective lever for reducing the risk of being misdirected in universities in South-Kivu, in the Democratic Republic of CongoReferences
Z. Keshf and S. Khanum, “Career Guidance and Counseling Needs in a Developing Country’s Context: A Qualitative Study,” Sage Open, vol. 11, no. 3, p. 21582440211040120, Jul. 2021, doi: 10.1177/21582440211040119.
M. Poncelet and P. Kapagama Ikando, “Private Higher Education in a Post-Abdication State: (In)Governance and Inequality in the Democratic Republic of Congo,” in Private Higher Education and Inequalities in the Global South: Lessons from Africa, Latin America and Asia, E. Gérard, Ed. Cham: Springer Nature Switzerland, 2024, pp. 223–268. doi: 10.1007/978-3-031-54756-0_7.
P. Perchinunno, M. Bilancia, and D. Vitale, “A Statistical Analysis of Factors Affecting Higher Education Dropouts,” Soc. Indic. Res., vol. 156, no. 2–3, pp. 341–362, Aug. 2021, doi: 10.1007/s11205-019-02249-y.
A. Pantoja-Vallejo and B. Berrios-Aguayo, “TIMONEL: Recommendation System Applied to the Educational Orientation of Higher Education Students,” in Innovation in Information Systems and Technologies to Support Learning Research, M. Serrhini, C. Silva, and S. Aljahdali, Eds. Springer International Publishing, 2020, pp. 14–26. doi: 10.1007/978-3-030-36778-7_2.
C. R. I. McAdams and V. A. Foster, “Promoting the Development of High-Risk College Students Through a Deliberate Psychological Education-Based Freshman Orientation Course,” J. Freshm. Year Exp. Students Transit., vol. 10, no. 1, pp. 51–72, 1998.
J. Ben Schafer, D. Frankowski, J. Herlocker, and S. Sen, “Collaborative Filtering Recommender Systems,” in The Adaptive Web, P. Brusilovsky, A. Kobsa, and W. Nejdl, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007, pp. 291–324. doi: 10.1007/978-3-540-72079-9_9.
D. Wang, Y. Liang, D. Xu, X. Feng, and R. Guan, “A content-based recommender system for computer science publications,” Knowledge-Based Syst., vol. 157, pp. 1–9, Oct. 2018, doi: 10.1016/j.knosys.2018.05.001.
J. K. Tarus, Z. Niu, and G. Mustafa, “Knowledge-based recommendation: a review of ontology-based recommender systems for e-learning,” Artif. Intell. Rev., vol. 50, no. 1, pp. 21–48, Jun. 2018, doi: 10.1007/s10462-017-9539-5.
L. Wenzhe and S. V Grigorev, “Implementation of the Demographic-Based Recommendation Algorithm Using Big Data,” in 2022 11th International Conference on Information Communication and Applications (ICICA), Jun. 2022, pp. 1–5. doi: 10.1109/ICICA56942.2022.00007.
R. Burke, “Hybrid Recommender Systems: Survey and Experiments,” User Model. User-adapt. Interact., vol. 12, no. 4, pp. 331–370, May 2002, doi: 10.1023/A:1021240730564.
M. Amane, K. Aissaoui, and M. Berrada, “ERSDO: E-learning Recommender System based on Dynamic Ontology,” Educ. Inf. Technol., vol. 27, no. 6, pp. 7549–7561, Jul. 2022, doi: 10.1007/s10639-022-10914-y.
O. EL AISSAOUI and L. OUGHDIR, “A learning style-based Ontology Matching to enhance learning resources recommendation,” in 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Apr. 2020, pp. 1–7. doi: 10.1109/IRASET48871.2020.9092142.
S. Assami, N. Daoudi, and R. Ajhoun, “Ontology-Based Modeling for a Personalized MOOC Recommender System,” in Information Systems and Technologies to Support Learning, Á. Rocha and M. Serrhini, Eds. Springer International Publishing, 2019, pp. 21–28. doi: 10.1007/978-3-030-03577-8_3.
L. Romero, C. Saucedo, M. L. Caliusco, and M. Gutiérrez, “Supporting self-regulated learning and personalization using ePortfolios: a semantic approach based on learning paths,” Int. J. Educ. Technol. High. Educ., vol. 16, no. 1, p. 16, Dec. 2019, doi: 10.1186/s41239-019-0146-1.
S. Bhaskaran, R. Marappan, and B. Santhi, “Design and Analysis of a Cluster-Based Intelligent Hybrid Recommendation System for E-Learning Applications,” Mathematics, vol. 9, no. 2, p. 197, Jan. 2021, doi: 10.3390/math9020197.
J. C. S. Perez, R. F. Manrique, O. Mariño, M. L. Vásquez, and N. Cardozo, “A course hybrid recommender system for limited information scenarios | Journal of Educational Data Mining,” J. Educ. Data Min., vol. 14, no. 3, pp. 162–188, May 2022, doi: 10.5281/zenodo.7304829.
N. Kamal, F. Sarker, A. Rahman, S. Hossain, and K. A. Mamun, “Recommender System in Academic Choices of Higher Education: A Systematic Review,” IEEE Access, vol. 12, pp. 35475–35501, May 2024, doi: 10.1109/ACCESS.2024.3368058.
K. K. San, H. H. Win, and K. E. E. Chaw, “Enhancing Hybrid Course Recommendation with Weighted Voting Ensemble Learning,” J. Futur. Artif. Intell. Technol., vol. 1, no. 4, pp. 337–347, Jan. 2025, doi: 10.62411/faith.3048-3719-55.
Z. Tagdimi, I. Amzil, Y. Jdidou, and S. Aammou, “Enhancing Innovation Through Bayesian Networks in Recommender Learning Paths,” in Technological Tools for Innovative Teaching, IGI Global Scientific Publishing, 2023, pp. 277–291. doi: 10.4018/979-8-3693-3132-3.ch014.
F. V Jensen and T. D. Nielsen, Eds., “Learning the Structure of Bayesian Networks,” in Bayesian Networks and Decision Graphs: February 8, 2007, New York, NY: Springer, 2007, pp. 229–264. doi: 10.1007/978-0-387-68282-2_7.
H. A. KARABOĞA and İ. DEMİR, “Examining the factors affecting students’ science success with Bayesian networks,” Int. J. Assess. Tools Educ., vol. 10, no. 3, pp. 413–433, Sep. 2023, doi: 10.21449/ijate.1218659.
S. Saeedi, D. Božanić, and R. Safa, “Strategic Analytics for Predicting Students’ Academic Performance Using Cluster Analysis and Bayesian Networks,” Educ. Sci. Manag., vol. 2, no. 4, pp. 197–214, Dec. 2024, doi: 10.56578/esm020402.
C. Conati, A. Gertner, and K. VanLehn, “Using Bayesian Networks to Manage Uncertainty in Student Modeling,” User Model. User-adapt. Interact., vol. 12, no. 4, pp. 371–417, May 2002, doi: 10.1023/A:1021258506583.
J. Xu and N. Dadey, “Using Bayesian Networks to Characterize Student Performance across Multiple Assessments of Individual Standards,” Appl. Meas. Educ., vol. 35, no. 3, pp. 179–196, Jul. 2022, doi: 10.1080/08957347.2022.2103134.
J. Tarbes, P. Morales, M. Levano, P. Schwarzenberg, O. Nicolis, and B. Peralta, “Explainable Prediction of Academic Failure Using Bayesian Networks,” in 2022 IEEE International Conference on Automation/XXV Congress of the Chilean Association of Automatic Control (ICA-ACCA), Oct. 2022, pp. 1–6. doi: 10.1109/ICA-ACCA56767.2022.10006086.
J. D. Johnson, L. Smail, D. Corey, and A. M. Jarrah, “Using Bayesian Networks to Provide Educational Implications: Mobile Learning and Ethnomathematics to Improve Sustainability in Mathematics Education,” Sustainability, vol. 14, no. 10, p. 5897, May 2022, doi: 10.3390/su14105897.
M. Baranyi, K. Gal, R. Molontay, and M. Szabo, “Modeling Students’ Academic Performance Using Bayesian Networks,” in 2019 17th International Conference on Emerging eLearning Technologies and Applications (ICETA), Nov. 2019, pp. 42–49. doi: 10.1109/ICETA48886.2019.9040067.
X. Wang, V. Hoo, M. Liu, J. Li, and Y. C. Wu, “Advancing legal recommendation system with enhanced Bayesian network machine learning,” Artif. Intell. Law, Nov. 2024, doi: 10.1007/s10506-024-09424-8.
X. Feng, “Research on the Design of Recommendation System for Learning Methods Based on Bayesian Networks,” in 2023 7th Asian Conference on Artificial Intelligence Technology (ACAIT), Nov. 2023, pp. 1239–1243. doi: 10.1109/ACAIT60137.2023.10528544.
L. M. Mwandigha, P. A. Tiffin, L. W. Paton, A. S. Kasim, and J. R. Böhnke, “What is the effect of secondary (high) schooling on subsequent medical school performance? A national, UK-based, cohort study,” BMJ Open, vol. 8, no. 5, p. e020291, May 2018, doi: 10.1136/bmjopen-2017-020291.
R. Igić, “Preparations of Students for Enrollment in Medical Schools,” J. Med. Educ. Curric. Dev., vol. 11, p. 23821205241264696, Jan. 2024, doi: 10.1177/23821205241264698.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Philippe Boribo kikunda, Jérémie Ndikumagenge, Longin Ndayisaba, Thierry Nsabimana
This work is licensed under a Creative Commons Attribution 4.0 International License.
