International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 18, No. 1, 8 Feb. 2026
Cover page and Table of Contents: PDF (size: 1454KB)
Developing a Bayesian Network Model to Predict Students' Performance Based on the Analysis of their Higher Education Trajectory
PDF (1454KB), PP.21-47
Views: 0 Downloads: 0
Author(s)
Index Terms
Bayesian Network, Higher Education Trajectory, Hill-Climbing Structure Learning Algorithm, Kullback-Leibler Divergence, Variable Elimination Inference Algorithm
Abstract
The Admission Point Score (APS) metric, commonly used to admit prospective students into academic programmes, may appear effective in predicting student success. In reality, almost 50% of students admitted to a science programme in a higher education institution failed to meet all the requirements necessary to complete the programme during the period of 2008 and 2015. This had a direct impact on the overall graduation throughput. This research therefore focuses on adopting a probabilistic-graphical approach as a viable alternative to the APS metric for determining student success trajectories in higher education. The purpose of this approach was to provide higher education institutions with a system to monitor students’ academic performance en-route to graduation from a probabilistic and graphical point of view. This research employed a probability distribution distance metric to ascertain how close the learned models were to the true model for varying sample sizes. The significance of these results addressed the need for knowledge discovery of dependencies that existed between the students’ module results in a higher education trajectory that spans three years.
Cite This Paper
Thabo Ramaano, Ashwini Jadhav, Ritesh Ajoodha, "Developing a Bayesian Network Model to Predict Students' Performance Based on the Analysis of their Higher Education Trajectory", International Journal of Modern Education and Computer Science(IJMECS), Vol.18, No.1, pp. 21-47, 2026. DOI:10.5815/ijmecs.2026.01.02
Reference
[1]T. Omphile and M. Lindikaya, "Estimating South African higher education productivity and its determinants using fare-primont index: Are historically disadvantaged universities catching up?," Research in Higher Education,2022, vol. 64, pp. 1–22, doi: 10.1007/s11162-022-09699-3.
[2]R. Maluleke, "Education Series Volume V Higher education and skills in South Africa. Technical report," Statistics South Africa, 2017.
[3]R. Ajoodha, "Identifying academically vulnerable learners in first-year science programmes at a South African higher-education institution", South African Computer Journal, South Africa, 2022, vol. 34, pp. 120–148, doi: https://doi.org/10.18489/sacj.v34i2.832.
[4]C. Haas and A. Hadjar, "Students’ trajectories through higher education: a review of quantitative research," Higher Education, 2020, vol. 79, doi: 10.1007/s10734-019-00458-5.
[5]H. Roslan and C. Jen Chen, "Educational data mining for student performance prediction: A systematic literature review (2015-2021)," International Journal of Emerging Technologies in Learning (iJET), 2022, vol. 17, pp. 147-179, doi: 10.3991/ijet.v17i05.27685.
[6]R. Bekele and W. Menzel, "A Bayesian approach to predict performance of a student (BAPPS): A case with Ethiopian students," IASTED International Conference on Artificial Intelligence and Applications, part of the 23rd Multi-Conference on Applied Informatics, Innsbruck, Austria, 2005, pp. 189-194.
[7]R. Torabi, P. Moradi and A. Khanteymoori, "Predict student scores using Bayesian networks," Procedia - Social and Behavioral Sciences, 2012, vol. 46, pp. 4476-4480, doi: 10.1016/j.sbspro.2012.06.280.
[8]Z. Nudelman, D. Moodley and S. Berman, "Using Bayesian networks and Machine learning to predict computer science success," 47th Annual Conference of the Southern African Computer Lecturers' Association, SACLA 2018, Gordon's Bay, South Africa, June 18–20, 2018, Revised Selected Papers, Springer CCIS 963, 2019, pp. 207-222, doi: 10.1007/978-3-030-05813-5_14.
[9]L. Mahmoud Abu Zohair, "Prediction of Student’s performance by modelling small dataset size," International Journal of Educational Technology in Higher Education, 2019, vol. 16, pp. 18, doi: 10.1186/s41239-019-0160-3.
[10]M. Mathye and R. Ajoodha "A Bayesian approach to predicting student performance using biographical and enrollment observations," unpublished, University of the Witwatersrand, South Africa, 2018.
[11]T. Kustitskaya, A. Kytmanov and M. Noskov, "Student-at-risk detection by current learning performance indicators using Bayesian networks," 2020, doi: 10.48550/arXiv.2004.09774.
[12]M. Cross and C. Carpentier, "'New Students; In South African higher education: Institutional Culture, student performance and the challenge of democratisation," Perspectives in Education, 2009, vol. 27, pp. 6-18.
[13]A. Almarabheh, M. Shehata, A. Ismaeel, H. Atwa and A. Jaradat, "Predictive validity of admission criteria in predicting academic performance of medical students: A retrospective cohort study," Frontiers in Medicine, 2022, doi: 10.3389/fmed.2022.971926.
[14]N. Mngadi, R. Ajoodha and A. Jadhav, "A theoretical model to predict undergraduate learner attrition using background, individual, and schooling attributes," unpublished, University of the Witwatersrand, South Africa, 2020.
[15]Q. El Aissaoui, Y. El Alami El Madani, L. Oughdir, A. Dakkak and Y. El Allioui (2020), "A Multiple Linear Regression-Based Approach to Predict Student Performance," Advanced Intelligent Systems for Sustainable Development (AI2SD’2019) , 2020, pp. 9-23, doi: 10.1007/978-3-030-36653-7_2.
[16]V. Tinto, "Drop-outs from higher education: a theoretical synthesis of recent research," Review of Educational Research, 1975, vol. 45, pp. 89-125, doi: 10.2307/1170024.
[17]T. Abed, R. Ajoodha and A. Jadhav, (2020) "A prediction model to improve student placement at a South African higher education institution,"2020 International SAUPEC/RobMech/PRASA Conference, 2020, pp. 1-6, doi: 10.1109/SAUPEC/RobMech/PRASA48453.2020.9041147.
[18]E. Buraimoh, R. Ajoodha and K. Padayachee, "Application of Machine Learning Techniques to the Prediction of Student Success," 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), 2021, pp. 1-6, doi: 10.1109/IEMTRONICS52119.2021.9422545.
[19]K. Al Mayahi and A. Mahmood, "Machine learning based predicting student academic success," 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), Brno, Czech Republic, 2020, pp. 264-268, doi: 10.1109/ICUMT51630.2020.9222435.
[20]V. Nedeva and T. Pehlivanova, "Students’ performance analyses using machine learning algorithms in WEKA," IOP Conference Series: Materials Science and Engineering, 2021, vol. 1031, pp. 012061, doi:10.1088/1757-899X/1031/1/012061.
[21]S. Rama, K. Jaladi and D. Devarapalli, "Bayesian network and variable elimination algorithm for reasoning under uncertainty," IJCSIT, 2012, vol. 3, pp. 5227-5230.
[22]Y. Zhou, "Structure learning of probabilistic graphical models: A comprehensive survey," ArXiv, 2011, vol. abs/1111.6925.
[23]F. Cozman 2000, "Generalizing variable elimination in Bayesian networks," Workshop on Probabilistic Reasoning in Artificial Intelligence, 2020.
[24]V. Mihajlovic and M. Petkovic, "Dynamic Bayesian networks: A state of the art," Europhysics Letters (epl), 2001.
[25]R. Ajoodha and B. Rosman, "Influence modelling and learning between dynamic Bayesian networks using score-based structure learning", PhD thesis, The University of the Witwatersrand, South Africa, 2018.
[26]J. Gámez, J. Mateo and J. Puerta, "Learning Bayesian networks by hill climbing: Efficient methods based on progressive restriction of the neighborhood," Data Mining and Knowledge Discovery, 2011, vol. 22, pp. 106-148, doi: 10.1007/s10618-010-0178-6.
[27]M. Zyphur and F. Oswald, "Bayesian estimation and inference: A user's guide," Journal of Management, 2013, vol. 41, pp. 390-420,doi: 10.1177/0149206313501200.
[28]S. Moral, A. Cano and M. Gómez-Olmedo, "Computation of Kullback– Leibler divergence in Bayesian networks," Entropy, 2021, vol. 23, pp. 1122, doi: 10.3390/e23091122.
[29]M. Tubia, C. Bielza and P. Larranaga, "Facilitating the inference interpretation in Bayesian networks," unpublished, Universidad Politecnica de Madrid, 2023.
[30]A. Grim and P. Felzenszwalb, "Message passing dynamics of belief propagation algorithms," PhD thesis, Brown University, 2022.
[31]D. Ren, J. Guo and X. Hao, "Bayesian network variable elimination method optimal elimination order construction," ITM Web Conf, 2022, vol. 45, pp. 01012, doi: https://doi.org/10.1051/itmconf/20224501012.
[32]C. Aslay, M. Ciaperoni, A. Gionis and M. Mathioudakis, "Query the model: precomputations for efficient inference with Bayesian networks," ArXiv, 2019, vol. abs/1904.00079.
[33]I. Simonsson, "Exact inference in Bayesian networks and applications in forensic statistics," PhD thesis, Chalmers University of Technology and University of Gothenburg, 2018.