Design and Implementation of a Cyclic Dropout Preven-tion Model Using Institutional Research Data
DOI:
https://doi.org/10.52731/lir.v006.479Keywords:
Dropout Prediction, Institutional Research (IR), Student Support, Cyclic Intervention ModelAbstract
This position paper proposes a cyclic model for dropout prevention in higher education, integrating data-driven prediction and student support practices. The model connects six key phases—data consolidation, time-series dropout risk prediction, student status monitoring, classification of student trajectories, targeted intervention, and evaluation of support effectiveness—into a continuous improvement cycle. Grounded in institutional research (IR), the model utilizes attendance records, academic performance, and pre-admission data to estimate dropout probabilities and classify students using clustering techniques such as X-means. Based on these classifications, tailored interventions including early alert systems and enhanced first-year education programs are implemented. The effectiveness of these interventions is evaluated through changes in attendance and academic outcomes, enabling feedback into the model for refinement. This framework aims to bridge the gap between predictive analytics and practical student support, offering a scalable and adaptable approach for universities seeking to reduce dropout rates and improve student success.
References
Ministry of Education, Culture, Sports, Science and Technology. [Survey on the status of student enrollment (drop-outs and leaves of absence) (as of the end of the 2022 academic year)] “Gakusei no shugakujokyo (Chutai, Kyugaku) tou ni kansuru Chosa no Kekka ni Tsuite (in Japanese)”. 2023.
Yomiuri Shimbun Kyoiku Network, [University Competencies 2019] ”Daigaku no Jitsuryoku 2019 (in Japanese)”,Chuo Koron Shinsho, 2018.
V. Tinto, “Dropout from higher education: A theoretical synthesis of recent re-search,” Review of Educational Research, vol. 45, no. 1, pp. 89–125, 1975.
J. P. Bean and B. S. Metzner, “A conceptual model of nontraditional undergraduate student attrition,” Review of Educational Research, vol. 55, no. 4, pp. 485–540, 1985.
E. Kerby, “Toward a new theoretical model of student persistence in higher educa-tion,” Review of Higher Education, vol. 40, no. 3, pp. 327–356, 2017.
B. Carballo-Mendívil, A. Arellano-González, N. J. Ríos-Vázquez, and M. del P. Lizardi-Duarte, “Predicting student dropout from day one: XGBoost-based early warning system using pre-enrollment data,” Applied Sciences, vol. 15, no. 16, p. 9202, 2025.
M. Nagy and R. Molontay, “Interpretable dropout prediction: Towards XAI-based personalized intervention,” International Journal of Artificial Intelligence in Educa-tion, vol. 34, pp. 274–300, 2024.
N. Shiratori, S. Tairi, T. Oishi, M. Mori, and M. Murota, “Analysis of the influence of learning state before university admission to college dropout using hierarchical Bayesian model,” presented at NPSE Int. Conf. on Science Education, 2019.
O. Goren, L. Cohen, and A. Rubinstein, “Early prediction of student dropout in higher education using machine learning models,” in Proc. 17th Int. Conf. Educa-tional Data Mining (EDM), 2024, pp. 349–361.
N. Shiratori et al., “Identifying the high-risk duration to the semester to drop out of college using dropout probability,” IIAI Letters on Institutional Research, vol. 3, 2024.
N. Shiratori, S. Tajiri, T. Oishi, M. Mori, and M. Murota, “Making dropout patterns using transition of dropout probability,” Japan Journal of Educational Technology, vol. 44, no. 1, pp. 11–22, 2020.
D. Bañeres, M. E. Rodríguez-González, A.-E. Guerrero-Roldán, and P. Cortadas, “An early warning system to identify and intervene online dropout learners,” In-ternational Journal of Educational Technology in Higher Education, vol. 20, no. 3, 2023.
B. Gonzalez, T. P. Mendes, R. Pinto, S. V. Correia, S. Albuquerque, and P. Paulino, “Predictors of higher education dropout intention in the post-pandemic era: The mediating role of academic exhaustion,” PLOS One, vol. 20, no. 7, p. e0327643, 2025.
S. Plak, I. Cornelisz, M. Meeter, and C. van Klaveren, “Early warning systems for more effective student counselling in higher education: Evidence from a Dutch field experiment,” Higher Education Quarterly, vol. 76, pp. 131–152, 2022.
