PREDICTIVE LEARNING ANALYTICS FOR STUDENT RETENTION IN DIGITAL DISTANCE EDUCATION: MODELS AND ECONOMIC IMPLICATIONS

Rustam Yakhshiboev

Авторы

Rustam Yakhshiboev Автор

Ключевые слова:

predictive learning analytics, student retention, dropout prediction, distance education, early warning system, machine learning, cost–benefit analysis, return on investment, algorithmic fairness, higher education economics

Аннотация

Student attrition remains a persistent weakness of distance education, causing losses for learners, universities and society. Predictive learning analytics (PLA), which uses institutional and digital trace data to identify students at risk of dropping out, is increasingly promoted as a remedy, yet its economic value is rarely assessed. This article aims to synthesise evidence on the models used to identify at-risk students in digital distance education and to determine the conditions under which their use is economically justified. The study combines an integrative review of 31 publications from 2013–2026, covering predictive modelling studies, intervention evaluations, systematic reviews and research on fairness and dropout economics, with a scenariobased cost–benefit model of an early warning system for a cohort of 1,000 students. The review shows that models based on learning platform activity and assessment results reach high discrimination, with AUC values mostly between 0.8 and 0.95, that accuracy increases as the course progresses, and that pre-entry data alone predict dropout poorly. Evidence on retention effects is mixed: teachers' use of predictions was associated with better pass rates, whereas two controlled evaluations found no effect of prediction-driven support on dropout. The economic model shows that prediction without an effective intervention generates only costs and that the break-even intervention effectiveness ranges from 3.7% to 13.9% of correctly identified at-risk students. The effectiveness and cost of interventions affect profitability more than marginal gains in model accuracy. Practical recommendations on data integration, model choice, intervention design and budgeting are formulated for distance education providers in Uzbekistan.

Биография автора

Rustam Yakhshiboev

PhD, Associate Professor, Tashkent State University of Economics, Tashkent, Uzbekistan

Библиографические ссылки

1. On Education: Law of the Republic of Uzbekistan No. ZRU-637 of 23.09.2020 [Electronic resource]. – URL: https://lex.uz/docs/5013009

2. On approval of the Concept for the development of the higher education system of the Republic of Uzbekistan until 2030: Decree of the President of the Republic of Uzbekistan No. UP-5847 of 08.10.2019 [Electronic resource]. – URL: https://lex.uz/docs/4545887

3. On approval of the Strategy for the development of artificial intelligence technologies until 2030: Resolution of the President of the Republic of Uzbekistan No. PP-358 of 14.10.2024 [Electronic resource]. – URL: https://lex.uz/docs/7158606

4. Aina C., Baici E., Casalone G. [et al.] The determinants of university dropout: A review of the socio-economic literature // Socio-Economic Planning Sciences. – 2022. – Vol. 79. – Art. 101102. – DOI: 10.1016/j.seps.2021.101102.

5. Albreiki B., Zaki N., Alashwal H. A systematic literature review of student' performance prediction using machine learning techniques // Education Sciences. – 2021. – Vol. 11, No. 9. – Art. 552. – DOI: 10.3390/educsci11090552.

6. Aljohani N.R., Fayoumi A., Hassan S.-U. Predicting at-risk students using clickstream data in the virtual learning environment // Sustainability. – 2019. – Vol. 11, No. 24. – Art. 7238. – DOI: 10.3390/su11247238.

7. Baker R.S., Hawn A. Algorithmic bias in education // International Journal of Artificial Intelligence in Education. – 2022. – Vol. 32, No. 4. – P. 1052–1092. – DOI: 10.1007/s40593-021-00285-9.

8. Bañeres D., Rodríguez M.E., Guerrero-Roldán A.E. [et al.] An early warning system to detect atrisk students in online higher education // Applied Sciences. – 2020. – Vol. 10, No. 13. – Art. 4427. – DOI: 10.3390/app10134427.

9. Behr A., Giese M., Teguim Kamdjou H.D. [et al.] Dropping out of university: a literature review // Review of Education. – 2020. – Vol. 8, No. 2. – P. 614–652. – DOI: 10.1002/rev3.3202.

10. Bettahi A., Belouadha F.-Z., Harroud H. A modular and explainable machine learning pipeline for student dropout prediction in higher education // Algorithms. – 2025. – Vol. 18, No. 10. – Art. 662. – DOI: 10.3390/a18100662.

11. Bettinger E.P., Baker R.B. The effects of student coaching: An evaluation of a randomized experiment in student advising // Educational Evaluation and Policy Analysis. – 2014. – Vol. 36, No. 1. – P. 3–19. – DOI: 10.3102/0162373713500523.

12. Bird K.A., Castleman B.L., Mabel Z. [et al.] Bringing transparency to predictive analytics: A systematic comparison of predictive modeling methods in higher education // AERA Open. – 2021. – Vol. 7. – DOI: 10.1177/23328584211037630.

13. Conijn R., Snijders C., Kleingeld A. [et al.] Predicting student performance from LMS data: A comparison of 17 blended courses using Moodle LMS // IEEE Transactions on Learning Technologies. – 2017. – Vol. 10, No. 1. – P. 17–29. – DOI: 10.1109/TLT.2016.2616312.

14. Dawson S., Jovanović J., Gašević D. [et al.] From prediction to impact: Evaluation of a learning analytics retention program // Proceedings of the Seventh International Learning Analytics & Knowledge Conference (LAK'17). – New York: ACM, 2017. – P. 474–478. – DOI:

10.1145/3027385.3027405.

15. Gardner J., Brooks C., Baker R. Evaluating the fairness of predictive student models through slicing analysis // Proceedings of the 9th International Conference on Learning Analytics & Knowledge (LAK19). – New York: ACM, 2019. – P. 225–234. – DOI: 10.1145/3303772.3303791.

16. Gašević D., Dawson S., Rogers T. [et al.] Learning analytics should not promote one size fits all: The effects of instructional conditions in predicting academic success // The Internet and Higher Education. – 2016. – Vol. 28. – P. 68–84. – DOI: 10.1016/j.iheduc.2015.10.002.

17. Glandorf D., Lee H.R., Orona G.A. [et al.] Temporal and between-group variability in college dropout prediction // Proceedings of the 14th Learning Analytics and Knowledge Conference (LAK '24). – New York: ACM, 2024. – DOI: 10.1145/3636555.3636906.

18. Goren O., Cohen L., Rubinstein A. Early prediction of student dropout in higher education using machine learning models // Proceedings of the 17th International Conference on Educational Data Mining (EDM 2024). – Atlanta: International Educational Data Mining Society, 2024. – P. 349–359. – DOI: 10.5281/zenodo.12729834.

19. Herodotou C., Rienties B., Boroowa A. [et al.] A large-scale implementation of predictive learning analytics in higher education: the teachers' role and perspective // Educational Technology Research and Development. – 2019. – Vol. 67, No. 5. – P. 1273–1306. – DOI: 10.1007/s11423-019-09685-0.

20. Herodotou C., Hlosta M., Boroowa A. [et al.] Empowering online teachers through predictive learning analytics // British Journal of Educational Technology. – 2019. – Vol. 50, No. 6. – P. 3064–3079. – DOI: 10.1111/bjet.12853.

21. Herodotou C., Rienties B., Verdin B. [et al.] Predictive learning analytics “at scale”: Guidelines to successful implementation in higher education based on the case of the Open University UK // Journal of Learning Analytics. – 2019. – Vol. 6, No. 1. – P. 85–95. – DOI: 10.18608/jla.2019.61.5.

22. Herodotou C., Rienties B., Hlosta M. [et al.] The scalable implementation of predictive learning analytics at a distance learning university: Insights from a longitudinal case study // The Internet and Higher Education. – 2020. – Vol. 45. – Art. 100725. – DOI: 10.1016/j.iheduc.2020.100725.

23. Hlosta M., Herodotou C., Papathoma T. [et al.] Predictive learning analytics in online education: A deeper understanding through explaining algorithmic errors // Computers and Education: Artificial Intelligence. – 2022. – Vol. 3. – Art. 100108. – DOI: 10.1016/j.caeai.2022.100108.

24. Ifenthaler D., Yau J.Y.-K. Utilising learning analytics to support study success in higher education: a systematic review // Educational Technology Research and Development. – 2020. – Vol. 68, No. 4. – P. 1961–1990. – DOI: 10.1007/s11423-020-09788-z.

25. Kuzilek J., Hlosta M., Zdrahal Z. Open University Learning Analytics dataset // Scientific Data. – 2017. – Vol. 4. – Art. 170171. – DOI: 10.1038/sdata.2017.171.

26. Levin H.M., McEwan P.J., Belfield C. [et al.] Economic evaluation in education: Costeffectiveness and benefit-cost analysis. – 3rd ed. – Los Angeles: SAGE, 2018. – ISBN 978-1-4833-8180-0.

27. Plak S., Cornelisz I., Meeter M. [et al.] Early warning systems for more effective student counselling in higher education: Evidence from a Dutch field experiment // Higher Education Quarterly. – 2022. – Vol. 76, No. 1. – P. 131–152. – DOI: 10.1111/hequ.12298.

28. Prenkaj B., Velardi P., Stilo G. [et al.] A survey of machine learning approaches for student dropout prediction in online courses // ACM Computing Surveys. – 2021. – Vol. 53, No. 3. – P. 1– 34. – DOI: 10.1145/3388792.

29. Queiroga E.M., Lopes J.L., Kappel K. [et al.] A learning analytics approach to identify students at risk of dropout: A case study with a technical distance education course // Applied Sciences. – 2020. – Vol. 10, No. 11. – Art. 3998. – DOI: 10.3390/app10113998.

30. Sghir N., Adadi A., Lahmer M. Recent advances in predictive learning analytics: A decade systematic review (2012–2022) // Education and Information Technologies. – 2023. – Vol. 28, No. 7. – P. 8299–8333. – DOI: 10.1007/s10639-022-11536-0.

31. Simpson O. Student retention in distance education: are we failing our students? // Open Learning: The Journal of Open, Distance and e-Learning. – 2013. – Vol. 28, No. 2. – P. 105–119. – DOI: 10.1080/02680513.2013.847363.

32. Slade S., Prinsloo P. Learning analytics: Ethical issues and dilemmas // American Behavioral Scientist. – 2013. – Vol. 57, No. 10. – P. 1510–1529. – DOI: 10.1177/0002764213479366.

33. Snyder H. Literature review as a research methodology: An overview and guidelines // Journal of Business Research. – 2019. – Vol. 104. – P. 333–339. – DOI: 10.1016/j.jbusres.2019.07.039.

34. Sønderlund A.L., Hughes E., Smith J. The efficacy of learning analytics interventions in higher education: A systematic review // British Journal of Educational Technology. – 2019. – Vol. 50, No. 5. – P. 2594–2618. – DOI: 10.1111/bjet.12720.

35. Tsai Y.-S., Rates D., Moreno-Marcos P.M. [et al.] Learning analytics in European higher education – Trends and barriers // Computers & Education. – 2020. – Vol. 155. – Art. 103933. – DOI: 10.1016/j.compedu.2020.103933.

36. Waheed H., Hassan S.-U., Aljohani N.R. [et al.] Predicting academic performance of students from VLE big data using deep learning models // Computers in Human Behavior. – 2020. – Vol. 104. – Art. 106189. – DOI: 10.1016/j.chb.2019.106189.