Learning Analytics of Timing-Based Enrollment Behaviors for Early Academic Attrition Prediction
DOI:
https://doi.org/10.67151/rujbas.v1i1.38Keywords:
Learning analytics, transferability, academic attrition, late course drops, enrollment behaviors, transactional logs, early warning systemsAbstract
This paper investigates the predictive power of timing-based enrollment behaviors in response to a practical institutional need for an early warning system aimed at reducing academic attrition associated with late course drops. A learning analytics methodology has been adopted to examine three timing-based behavioral indicators: late enrollment, academic planning regularity, and enrollment procrastination, as early predictors of late course drop across three analytical levels, micro (course-level), meso (semester-level), and macro (program-level). More specifically, the three timing-based enrollment behaviors have been extracted from students’ transactional enrollment logs of 13 semesters, and logistic regression analysis between each indicator and late course drop, at each level, have been conducted. The findings indicate that both late enrollment and enrollment procrastination are robust positive predictors of academic risk across all analytical scales (p<0.001), with effect sizes becoming most pronounced at the programmatic level (Odds ratio=34.54 for late enrollment). In contrast, academic planning regularity emerged as a protective indicator (Odds ratio=0.404 at the meso level) associated with improved preparedness for semester workload demands. The findings support the transferability of timing-based behavioral indicators analytics while providing actionable intelligence for institutional Early Warning Systems to enable earlier and more targeted student interventions before critical academic loss occurs.
References
[1] Papamitsiou Z, Economides AA. Learning analytics and educational data mining in practice: a systematic literature review of empirical evidence. Educational Technology & Society. 2014;17(4):49-64.
[2] Gray G, McGuinness C, Owende P, Carthy A. A review of psychometric data analysis and applications in modelling of academic achievement in tertiary education. Journal of Learning Analytics. 2014;1(1):75-106. DOI: https://doi.org/10.18608/jla.2014.11.5
[3] Albreiki B, Zaki N, Alashwal H. A systematic literature review of student’ performance prediction using machine learning techniques. Education Sciences. 2021;11(9):552. https://doi.org/10.3390/educsci11090552 DOI: https://doi.org/10.3390/educsci11090552
[4] Alyahyan E, Düştegör D. Predicting academic success in higher education: literature review and best practices. International Journal of Educational Technology in Higher Education. 2020;17(1):3. https://doi.org/10.1186/s41239-020-0177-7 DOI: https://doi.org/10.1186/s41239-020-0177-7
[5] López-Zambrano J, Torralbo JAL, Romero C. Early prediction of student learning performance through data mining: a systematic review. Psicothema. 2021;33(3):456-65. https://doi.org/10.7334/psicothema2021.62 DOI: https://doi.org/10.7334/psicothema2021.62
[6] Borchers C, Xu Y, Pardos ZA. Are you an early dropper or late shopper? Mining enrollment transaction data to study procrastination in higher education. In: Proceedings of the 17th International Conference on Educational Data Mining (EDM 2024); 2024 Jul 14-17; Atlanta, GA. 2024. p. 426-33. https://doi.org/10.35542/osf.io/zud7q DOI: https://doi.org/10.35542/osf.io/zud7q
[7] Lenchner E. Mining transactional student-level data to predict community college student outcomes [PhD Thesis]. New York, NY: Columbia University; 2017.
[8] Xu Y, Pardos ZA. Mining detailed course transaction records for semantic information. In: Feng M, Käser T, Talukdar P, editors. Proceedings of the 16th International Conference on Educational Data Mining (EDM 2023); 2023 Jul; Bengaluru, India. International Educational Data Mining Society; 2023. p. 388-395. https://doi.org/10.5281/zenodo.8115794
[9] Borchers C, Xu Y, Pardos ZA. Workload overload? late enrollment leads to course dropout. Journal of Educational Data Mining. 2025;17(1):126-156. https://doi.org/10.5281/zenodo.14907388
[10] Hagedorn LS, Maxwell WE, Cypers S, Moon HS, Lester J. Course shopping in urban community colleges: an analysis of student drop and add activities. The Journal of Higher Education. 2007;78(4):464-85. https://doi.org/10.1080/00221546.2007.11772324 DOI: https://doi.org/10.1080/00221546.2007.11772324
[11] Hellas A, Ihantola P, Petersen A, Ajanovski VV, Gutica M, Hynninen T, et al. Predicting academic performance: a systematic literature review. In: Proceedings Companion of the 23rd Annual ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE 2018 Companion); 2018 Jul 2-4; Larnaca, Cyprus. New York, NY: ACM; 2018. p. 175–199. https://doi.org/10.1145/3293881.3295783 DOI: https://doi.org/10.1145/3293881.3295783
[12] Bohler J, Sherman S, Larson B, Mills H. Using registration timing as an early indicator of at-risk students in an online stem course. In: Proceedings of the Informing Science and Information Technology Education Conference (InSITE 2023); 2023 Jul 5-6. Santa Rosa (CA): Informing Science Institute; 2023. Article 12. https://doi.org/10.28945/5151 DOI: https://doi.org/10.28945/5151
[13] Namoun A, Alshanqiti A. Predicting student performance using data mining and learning analytics techniques: a systematic literature review. Applied Sciences. 2021;11(1):237. https://doi.org/10.3390/app11010237 DOI: https://doi.org/10.3390/app11010237
[14] Admass WS. Review on predicting student academic performance using data mining classification algorithm. Journal of Computer Engineering & Information Technology. 2021;10(11).
[15] Summers MD. Enrollment and registration behaviors as predictors of academic outcomes for full-time students in a rural community college [PhD Thesis]. Urbana, IL: University of Illinois at Urbana-Champaign; 2000.
[16] Deeva G, Snoeck M, De Weerdt J. Discovering the impact of students’ modeling behavior on their final performance. In: Buchmann R, Karagiannis D, Kirikova M, editors. The Practice of Enterprise Modeling. PoEM 2018. Lecture Notes in Business Information Processing. Cham: Springer; 2018. p. 335-50. https://doi.org/10.1007/978-3-030-02302-7_21 DOI: https://doi.org/10.1007/978-3-030-02302-7_21
[17] Shahiri AM, Husain W, Rashid NA. A review on predicting student’s performance using data mining techniques. Procedia Computer Science. 2015;72:414–22. https://doi.org/10.1016/j.procs.2015.12.157 DOI: https://doi.org/10.1016/j.procs.2015.12.157
[18] Ameen AO, Alarape MA, Adewole KS. Students’ academic performance and dropout predictions: a review. Malaysian Journal of Computing. 2019;4(2):278–303. https://doi.org/10.24191/mjoc.v4i2.6701 DOI: https://doi.org/10.24191/mjoc.v4i2.6701
[19] Macfadyen LP, Dawson S. Mining LMS data to develop an ‘‘early warning system” for educators: a proof of concept. Computers & Education. 2010;54(2):588–99. https://doi.org/10.1016/j.compedu.2009.09.008 DOI: https://doi.org/10.1016/j.compedu.2009.09.008
[20] Baker RSJD, Yacef K. The state of educational data mining in 2009: a review and future visions. Journal of Educational Data Mining. 2009;1(1):3–17. https://doi.org/10.5281/zenodo.3554657
[21] Wang X, Yu X, Guo L, Liu F, Xu L. Student performance prediction with short-term sequential campus behaviors. Information. 2020;11(4):201. https://doi.org/10.3390/info11040201 DOI: https://doi.org/10.3390/info11040201
[22] Sun H, He S, Esho O. Students performance prediction by mining behavioural pattern. Journal of Physics: Conference Series. 2021;1881:042051. https://doi.org/10.1088/1742-6596/1881/4/042051 DOI: https://doi.org/10.1088/1742-6596/1881/4/042051
[23] Siefken J. Registration delay and student performance. Journal of the Scholarship of Teaching and Learning. 2017;17(2):45–52. https://doi.org/10.14434/josotl.v17i2.20754 DOI: https://doi.org/10.14434/josotl.v17i2.20754
[24] Wäschle K, Allgaier A, Lachner A, Fink S, Nückles M. Procrastination and self-efficacy: tracing vicious and virtuous circles in self-regulated learning. Learning and Instruction. 2014;29:103–14. https://doi.org/10.1016/j.learninstruc.2013.09.005 DOI: https://doi.org/10.1016/j.learninstruc.2013.09.005
[25] You JW. Examining the effect of academic procrastination on achievement using LMS data in e-learning. Educational Technology & Society. 2015;18(3):64-74.
[26] Cui Y, Chen F, Shiri A, Fan Y. Predictive analytic models of student success in higher education: a review of methodology. Information and Learning Sciences. 2019;120(3-4):208–27. https://doi.org/10.1108/ILS-10-2018-0104 DOI: https://doi.org/10.1108/ILS-10-2018-0104
[27] Tan FZ, Chan WH. Interpreting student performance through predictive learning analytics. International Journal of Innovative Computing. 2024;14(2):1–13. https://doi.org/10.11113/ijic.v14n2.434 DOI: https://doi.org/10.11113/ijic.v14n2.434
Downloads
Published
Issue
Section
License
Copyright (c) 2026 2026 The Author. Published by Ar-Rasheed Smart University, Yemen
This work is licensed under a Creative Commons Attribution 4.0 International License.
