International Journal of

ADVANCED AND APPLIED SCIENCES

EISSN: 2313-3724, Print ISSN: 2313-626X

Frequency: 12

line decor
  
line decor

 Volume 13, Issue 4 (April 2026), Pages: 16-34

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

 Review Paper

Integrating machine learning practicality into learning analytics: A framework for reproducible and actionable dropout prediction models

 Author(s): 

Sabine Berger 1, Abeer Alsadoon 1, 2, Oday D. Jerew 1, 2, Ahmed Hamza Osman 3, *, Albaraa Abuobieda 4, Abubakar Elsafi 5, Azhari Qismallah 6

 Affiliation(s):

1Higher Education Leadership Institute (HELI), Melbourne, Australia
2Asia Pacific International College (APIC), Sydney, Australia
3Department of Information Systems, Faculty of Computing and Information Technology in Rabigh, King Abdulaziz University, Jeddah, Saudi Arabia
4Department of Computer Science, University of Tabuk, Tabuk, Saudi Arabia
5College of Computer Science and Engineering, Department of Software Engineering, University of Hafr Al Batin, Hafr Al Batin, Saudi Arabia
6Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia

 Full text

    Full Text - PDF

 * Corresponding Author. 

   Corresponding author's ORCID profile:  https://orcid.org/0000-0002-8512-578X

 Digital Object Identifier (DOI)

  https://doi.org/10.21833/ijaas.2026.04.003

 Abstract

Interest in learning analytics for predicting student dropout has increased in recent years; however, a clear gap remains between research findings and their practical implementation in educational settings. This study systematically reviews 34 recent practical studies on learning analytics and dropout prediction to identify key gaps that limit the transfer of research into practice. Based on these gaps, we propose a novel six-layer framework that integrates research design, model optimization, and deployment considerations, providing a structured approach to conducting practical learning analytics research. The framework addresses critical issues, including reproducibility, generalizability, interpretability, actionability, and computational feasibility. We map the existing literature onto this framework using structured evaluation tables and find that most studies lack comprehensive attention to model practicality. Our framework contributes to the field by integrating theoretical and operational considerations at the research stage, thereby helping to bridge the gap between published research and real-world application. Furthermore, we introduce reproduction studies as a mechanism to promote innovation, particularly in improving model interpretability, generalizability, and actionability. Finally, we recommend adopting training time as a standard evaluation metric to strengthen the focus on practical feasibility in future research.

 © 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

Learning analytics, Dropout prediction, Model practicality, Interpretability, Computational feasibility

 Article history

Received 10 October 2025, Received in revised form 20 March 2026, Accepted 27 March 2026

 Acknowledgment

This project was funded by the Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, Saudi Arabia, under grant no. (GPIP: 282- 830-2024). The authors, therefore, acknowledge with thanks DSR for technical and financial support. 

 Compliance with ethical standards

 Conflict of interest: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

 Citation:

Berger S, Alsadoon A, Jerew OD, Osman AH, Abuobieda A, Elsafi A, and Qismallah A (2026). Integrating machine learning practicality into learning analytics: A framework for reproducible and actionable dropout prediction models. International Journal of Advanced and Applied Sciences, 13(4): 16-34

  Permanent Link to this page

 Figures

  Fig. 1 Fig. 2 Fig. 3 Fig. 4

 Tables

  Table 1 Table 2 Table 3 Table 4 Table 5 Table 6 Table 7

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

 References (53)

  1. Adejo OW and Connolly T (2018). Predicting student academic performance using multi-model heterogeneous ensemble approach. Journal of Applied Research in Higher Education, 10(1): 61-75. https://doi.org/10.1108/JARHE-09-2017-0113   [Google Scholar]

  2. Alamuddin R, Rossman D, and Kurzweil M (2019). Interim findings report from the MAAPS advising experiment. ITHAKA S+ R Report, Ithaka S+R, New York, USA. https://doi.org/10.18665/sr.311567   [Google Scholar]

  3. Arnold KE and Pistilli MD (2012). Course signals at Purdue: Using learning analytics to increase student success. In the Proceedings of the 2nd International Conference on Learning Analytics and Knowledge, Association for Computing Machinery, Vancouver, Canada: 267–270. https://doi.org/10.1145/2330601.2330666   [Google Scholar] PMid:22496114

  4. Barbeiro L, Gomes A, Correia FB, and Bernardino J (2024). A review of educational data mining trends. Procedia Computer Science, 237: 88-95. https://doi.org/10.1016/j.procs.2024.05.083   [Google Scholar]

  5. Collberg C and Proebsting TA (2016). Repeatability in computer systems research. Communications of the ACM, 59(3): 62-69. https://doi.org/10.1145/2812803   [Google Scholar]

  6. Cortez P and Silva A (2008). Student performance. UCI Machine Learning Repository, Irvine, USA.   [Google Scholar]

  7. Delen D, Davazdahemami B, and Rasouli Dezfouli E (2024). Predicting and mitigating freshmen student attrition: A local-explainable machine learning framework. Information Systems Frontiers, 26: 641-662. https://doi.org/10.1007/s10796-023-10397-3   [Google Scholar] PMid:37361887 PMCid:PMC10097523

  8. Du X, Yang J, and Hung JL (2020). An integrated framework based on latent variational autoencoder for providing early warning of at-risk students. IEEE Access, 8: 10110-10122. https://doi.org/10.1109/ACCESS.2020.2964845   [Google Scholar]

  9. Fahd K, Venkatraman S, Miah SJ, and Ahmed K (2022). Application of machine learning in higher education to assess student academic performance, at-risk, and attrition: A meta-analysis of literature. Education and Information Technologies, 27: 3743-3775. https://doi.org/10.1007/s10639-021-10741-7   [Google Scholar]

  10. Gundersen OE (2021). The fundamental principles of reproducibility. Philosophical Transactions of the Royal Society A, 379(2197): 20200210. https://doi.org/10.1098/rsta.2020.0210   [Google Scholar] PMid:33775150

  11. Hoca S and Dimililer N (2025). A machine learning framework for student retention policy development: A case study. Applied Sciences, 15(6): 2989. https://doi.org/10.3390/app15062989   [Google Scholar]

  12. Hoffait AS and Schyns M (2017). Early detection of university students with potential difficulties. Decision Support Systems, 101: 1-11. https://doi.org/10.1016/j.dss.2017.05.003   [Google Scholar]

  13. Huang H, Yuan S, He T, and Hou R (2022). Use of behavior dynamics to improve early detection of at-risk students in online courses. Mobile Networks and Applications, 27: 441-452. https://doi.org/10.1007/s11036-021-01844-z   [Google Scholar]

  14. Kuzilek J, Hlosta M, and Zdrahal Z (2017). Open university learning analytics dataset. Scientific Data, 4: 170171. https://doi.org/10.1038/sdata.2017.171   [Google Scholar] PMid:29182599 PMCid:PMC5704676

  15. Latif G, Abdelhamid SE, Fawagreh KS, Brahim GB, and Alghazo R (2023). Machine learning in higher education: Students’ performance assessment considering online activity logs. IEEE Access, 11: 69586-69600. https://doi.org/10.1109/ACCESS.2023.3287972   [Google Scholar]

  16. Loyola-González O (2019). Black-box vs. white-box: Understanding their advantages and weaknesses from a practical point of view. IEEE Access, 7: 154096-154113. https://doi.org/10.1109/ACCESS.2019.2949286   [Google Scholar]

  17. Maniyan S, Ghousi R, and Haeri A (2024). Data mining-based decision support system for educational decision makers: Extracting rules to enhance academic efficiency. Computers and Education: Artificial Intelligence, 6: 100242. https://doi.org/10.1016/j.caeai.2024.100242   [Google Scholar]

  18. Masood JAIS, Chakravarthy NK, Asirvatham D, Marjani M, Shafiq DA, and Nidamanuri S (2024). A hybrid deep learning model to predict high-risk students in virtual learning environments. IEEE Access, 12: 103687-103703. https://doi.org/10.1109/ACCESS.2024.3434644   [Google Scholar]

  19. Matz SC, Bukow CS, Peters H, Deacons C, Dinu A, and Stachl C (2023). Using machine learning to predict student retention from socio-demographic characteristics and app-based engagement metrics. Scientific Reports, 13: 5705. https://doi.org/10.1038/s41598-023-32484-w   [Google Scholar] PMid:37029155 PMCid:PMC10082180

  20. Memarian B and Doleck T (2023). Fairness, accountability, transparency, and ethics (FATE) in artificial intelligence (AI) and higher education: A systematic review. Computers and Education: Artificial Intelligence, 5: 100152. https://doi.org/10.1016/j.caeai.2023.100152   [Google Scholar]

  21. Molla-Esparza C, Gómez-Núñez MI, and García-García FJ (2025). Applications of learning analytics in the study of academic performance in higher education: A pilot-tested meta-review protocol. International Journal of Educational Research Open, 8: 100433. https://doi.org/10.1016/j.ijedro.2024.100433   [Google Scholar]

  22. Mosia M (2025). A Bayesian state-space approach to dynamic hierarchical logistic regression for evolving student risk in educational analytics. Data, 10(2): 23. https://doi.org/10.3390/data10020023   [Google Scholar]

  23. Mustofa S, Emon YR, Mamun SB, Akhy SA, and Ahad MT (2025). A novel AI-driven model for student dropout risk analysis with explainable AI insights. Computers and Education: Artificial Intelligence, 8: 100352. https://doi.org/10.1016/j.caeai.2024.100352   [Google Scholar]

  24. Nabil A, Seyam M, and Abou-Elfetouh A (2021). Prediction of students’ academic performance based on courses’ grades using deep neural networks. IEEE Access, 9: 140731-140746. https://doi.org/10.1109/ACCESS.2021.3119596   [Google Scholar]

  25. Nagy M and Molontay R (2024). Interpretable dropout prediction: Towards XAI-based personalized intervention. International Journal of Artificial Intelligence in Education, 34: 274-300. https://doi.org/10.1007/s40593-023-00331-8   [Google Scholar]

  26. Olaya D, Vásquez J, Maldonado S, Miranda J, and Verbeke W (2020). Uplift modeling for preventing student dropout in higher education. Decision Support Systems, 134: 113320. https://doi.org/10.1016/j.dss.2020.113320   [Google Scholar]

  27. Ortigosa A, Carro RM, Bravo-Agapito J, Lizcano D, Alcolea JJ, and Blanco O (2019). From lab to production: Lessons learnt and real-life challenges of an early student-dropout prevention system. IEEE Transactions on Learning Technologies, 12(2): 264-277. https://doi.org/10.1109/TLT.2019.2911608   [Google Scholar]

  28. Pan F, Zhang H, Li X, Zhang M, and Ji Y (2024). Achieving optimal trade-off for student dropout prediction with multi-objective reinforcement learning. PeerJ Computer Science, 10: e2034. https://doi.org/10.7717/peerj-cs.2034   [Google Scholar] PMid:38855215 PMCid:PMC11157558

  29. Pek RZ, Özyer ST, Elhage T, Özyer T, and Alhajj R (2023). The role of machine learning in identifying students at-risk and minimizing failure. IEEE Access, 11: 1224-1243. https://doi.org/10.1109/ACCESS.2022.3232984   [Google Scholar]

  30. Rabelo AM and Zárate LE (2025). A model for predicting dropout of higher education students. Data Science and Management, 8(1): 72-85. https://doi.org/10.1016/j.dsm.2024.07.001   [Google Scholar]

  31. Raghupathi W, Raghupathi V, and Ren J (2022). Reproducibility in computing research: An empirical study. IEEE Access, 10: 29207-29223. https://doi.org/10.1109/ACCESS.2022.3158675   [Google Scholar]

  32. Ramaswami G, Susnjak T, Mathrani A, and Umer R (2023). Use of predictive analytics within learning analytics dashboards: A review of case studies. Technology, Knowledge and Learning, 28: 959-980. https://doi.org/10.1007/s10758-022-09613-x   [Google Scholar]

  33. Rebelo Marcolino M, Reis Porto T, Thompsen Primo T, Targino R, Ramos V, Marques Queiroga E, Munoz R, and Cechinel C (2025). Student dropout prediction through machine learning optimization: Insights from moodle log data. Scientific Reports, 15: 9840. https://doi.org/10.1038/s41598-025-93918-1   [Google Scholar] PMid:40119104 PMCid:PMC11928464

  34. Romero S and Liao X (2025). Statistical and machine learning models for predicting university dropout and scholarship impact. PLOS ONE, 20(6): e0325047. https://doi.org/10.1371/journal.pone.0325047   [Google Scholar] PMid:40560971 PMCid:PMC12193850

  35. Roy K and Farid DM (2024). An adaptive feature selection algorithm for student performance prediction. IEEE Access, 12: 75577-75598. https://doi.org/10.1109/ACCESS.2024.3406252   [Google Scholar]

  36. Sailer M, Ninaus M, Huber SE, Bauer E, and Greiff S (2024). The end is the beginning is the end: The closed-loop learning analytics framework. Computers in Human Behavior, 158: 108305. https://doi.org/10.1016/j.chb.2024.108305   [Google Scholar]

  37. Sghir N, Adadi A, and Lahmer M (2023). Recent advances in predictive learning analytics: A decade systematic review (2012–2022). Education and Information Technologies, 28: 8299-8333. https://doi.org/10.1007/s10639-022-11536-0   [Google Scholar] PMid:36571084 PMCid:PMC9765383

  38. Siemens G (2013). Learning analytics: The emergence of a discipline. American Behavioral Scientist, 57(10): 1380-1400. https://doi.org/10.1177/0002764213498851   [Google Scholar]

  39. Skittou M, Merrouchi M, and Gadi T (2024). Development of an early warning system to support educational planning process by identifying at-risk students. IEEE Access, 12: 2260-2271. https://doi.org/10.1109/ACCESS.2023.3348091   [Google Scholar]

  40. Sonnleitner B, Madou T, Deceuninck M, Theodosiou F, and Sagaert YR (2025). Evaluation of early student performance prediction given concept drift. Computers and Education: Artificial Intelligence, 8: 100369. https://doi.org/10.1016/j.caeai.2025.100369   [Google Scholar]

  41. Tinto V (1975). Dropout from higher education: A theoretical synthesis of recent research. Review of Educational Research, 45(1): 89-125. https://doi.org/10.3102/00346543045001089   [Google Scholar]

  42. Tong T and Li Z (2025). Predicting learning achievement using ensemble learning with result explanation. PLOS ONE, 20(1): e0312124. https://doi.org/10.1371/journal.pone.0312124   [Google Scholar] PMid:39745993 PMCid:PMC11694977

  43. Topali P, Ortega-Arranz A, Rodríguez-Triana MJ, Er E, Khalil M, and Akçapınar G (2025). Designing human-centered learning analytics and artificial intelligence in education solutions: A systematic literature review. Behaviour & Information Technology, 44(5): 1071-1098. https://doi.org/10.1080/0144929X.2024.2345295   [Google Scholar]

  44. Vahdat M, Oneto L, Anguita D, Funk M, and Rauterberg M (2015). Educational process mining (EPM): A learning analytics data set. UCI Machine Learning Repository, Irvine, USA.   [Google Scholar]

  45. Van Petegem C, Deconinck L, Mourisse D, Maertens R, Strijbol N, Dhoedt B, De Wever B, Dawyndt P, and Mesuere B (2023). Pass/fail prediction in programming courses. Journal of Educational Computing Research, 61(1): 68-95. https://doi.org/10.1177/07356331221085595   [Google Scholar]

  46. Vives L, Cabezas I, Vives JC, Reyes NG, Aquino J, Cóndor JB, and Altamirano SFS (2024). Prediction of students’ academic performance in the programming fundamentals course using long short-term memory neural networks. IEEE Access, 12: 5882-5898. https://doi.org/10.1109/ACCESS.2024.3350169   [Google Scholar]

  47. Wen X and Juan H (2023). Early prediction of students’ performance using a deep neural network based on online learning activity sequence. Applied Sciences, 13(15): 8933. https://doi.org/10.3390/app13158933   [Google Scholar]

  48. West D, Huijser H, and Heath D (2016). Putting an ethical lens on learning analytics. Educational Technology Research and Development, 64: 903-922. https://doi.org/10.1007/s11423-016-9464-3   [Google Scholar]

  49. Wong A, Lee WL, Chan MSL, Tan YE, Huang JMK, and Lee YH (2025). Digital learning resources and student success: Analyzing engagement and academic performance. Journal of Applied Learning & Teaching, 8(S2): 45-54. https://doi.org/10.37074/jalt.2025.8.S2.3   [Google Scholar]

  50. Xiao W and Hu J (2023). A state‐of‐the‐art survey of predicting students' performance using artificial neural networks. Engineering Reports, 5(8): e12652. https://doi.org/10.1002/eng2.12652   [Google Scholar]

  51. Zanellati A, Zingaro SP, and Gabbrielli M (2024). Balancing performance and explainability in academic dropout prediction. IEEE Transactions on Learning Technologies, 17: 2086-2099. https://doi.org/10.1109/TLT.2024.3425959   [Google Scholar]

  52. Zhang X, Zhang Y, Chen AL, Yu M, and Zhang L (2025). Optimizing multi label student performance prediction with GNN-TINet: A contextual multidimensional deep learning framework. PLOS ONE, 20(1): e0314823. https://doi.org/10.1371/journal.pone.0314823   [Google Scholar] PMid:39841673 PMCid:PMC11753673

  53. Zhidkikh D, Heilala V, Van Petegem C, Dawyndt P, Jarvinen M, Viitanen S, and Hämäläinen R (2024). Reproducing predictive learning analytics in CS1: Toward generalizable and explainable models for enhancing student retention. Journal of Learning Analytics, 11(1): 132-150. https://doi.org/10.18608/jla.2024.7979   [Google Scholar]