Italian Journal of Health Education, Sports and Inclusive Didactics
Human-Centered AutoML for Early Student Dropout Prediction in Higher Education
Abstract
Student attrition in higher education is a multidimensional challenge shaped by demographic, academic, behavioral, and socioeconomic factors. This study proposes an AutoML 3.0 framework for early dropout prediction, grounded in educational persistence theory, learning analytics, and human-centered machine learning (HCML). The framework integrates evolutionary data-centric optimization (EDCA), domain-aware model selection, and human-in-the-loop oversight. Using a longitudinal dataset of 6,287 students (2014–2021), it embeds fairness auditing across age, gender, and socioeconomic subgroups, uncertainty calibration via Brier scores, and temporal cohort validation. The top configuration (FLAML + LightGBM) achieves 0.802 accuracy, 0.740 macro-F1 (95% CI: [0.71, 0.76]), and a Brier score of 0.14, reducing false negatives among older students by 18% and maintaining demographic parity below 5%. These results show that theoretically grounded, ethically aligned AutoML can deliver scalable and responsible early-warning systems in higher education.
Keywords
References
Abougalala, R. A., Alharbi, N., Amasha, M. A., Areed, M. F., Alkhalaf, S., & Khairy, D. (2025). Predicting student performance academic using automated machine learning (AutoML): In medical academic institutions. Journal of New Approaches in Educational Research, 14(1), 19.
Aboukacem, A., Mekouar, L., Bergou, E. H., Iraqi, Y., & Berrada, I. (2025). On the fairness of ensemble learning methods in student dropout prediction. In Proceedings of the International Conference on Artificial Intelligence in Education (pp. 364-371). Springer Nature Switzerland.
Astin, A. W. (2014). Student involvement: A developmental theory for higher education. In College student development and academic life (pp. 251-262). Routledge.
Ayyaswamy, K., Kathirvel, N., Gobinath, V. M., & Maheswaran, C. P. (2025). Effective leadership strategies for enhancing student success in higher education. In New horizons in leadership (pp. 61-92). IGI Global.
Azevedo, K., Quaranta, L., Calefato, F., & Kalinowski, M. (2024). A multivocal literature review on the benefits and limitations of automated machine learning tools. arXiv preprint arXiv:2401.11366.
Baratchi, M., Wang, C., Limmer, S., Van Rijn, J. N., Hoos, H., Bäck, T., & Olhofer, M. (2024). Automated machine learning: Past, present and future. Artificial Intelligence Review, 57(5), 122. https://doi.org/10.1007/s10462-024-10726-1
Bean, J., & Eaton, S. B. (2001). The psychology underlying successful retention practices. Journal of College Student Retention: Research, Theory & Practice, 3(1), 73-89. https://doi.org/10.2190/6R55-4B30-28XG-L8U0
Bento Junior, G. S., Bento, B. F. S., Ribeiro, U. F. C., & Santos, H. T. (2025). Dropout in higher education and Vincent Tinto's models: Bibliographical research. Educação e Pesquisa, 51, e285842. https://doi.org/10.1590/s1678-4634202551285842en
Berens, J., Diem, A., Rumert, L., Schneider, K., & Wolter, S. C. (2025). Crossing individual university boundaries: a comprehensive approach to predicting dropouts in the higher education system. Higher Education, 1-22.
Bernardo, A. B., García-Gutiérrez, V., Esteban, M., & Maluenda-Albornoz, J. (2025). Relationship between self-efficacy and university dropout: A systematic review. Frontiers in Psychology, 16, Article 1553485. https://doi.org/10.3389/fpsyg.2025.1553485
Blanco González, E., Bernardo Gutiérrez, A. B., Tuero Herrero, E., & Núñez Pérez, J. C. (2025). Academic stress, evaluation anxiety and university dropout intention: Mediating and moderating roles for resilience. Psicología Educativa, 21 (2).
Buñay-Guisñan, P., Lara, J. A., Cano, A., Cerezo, R., & Romero, C. (2026). Towards accessible AI for addressing students' academic dropout: An auto machine learning and explainable artificial intelligence approach. Universal Access in the Information Society, 25(1), 19. https://doi.org/10.1007/s10209-025-01234-5
Chavez-Sosa, J. V., Huancahuire-Vega, S., Casana Rojas, D. G., Terrones Huancas, D. A., Anaya Vilca, A. A., & Newball-Noriega, E. E. (2026). University dropout intention and its psychological dimensions: the role of academic stress in Peruvian students. In Frontiers in Education (Vol. 11, p. 1756633). Frontiers Media SA.
Cobo-Rendón, R., Hojman, V., García-Álvarez, D., & Cobo Rendon, R. (2023). Academic emotions, college adjustment, and dropout intention in university students. Frontiers in Education, 8, Article 1303765. https://doi.org/10.3389/feduc.2023.1303765
Deci, E. L., & Ryan, R. M. (2000). The "what" and "why" of goal pursuits: Human needs and the self-determination of behavior. Psychological Inquiry, 11(4), 227-268.
https://doi.org/10.1207/S15327965PLI1104_01
Dias-Broens, A. S., Meeuwisse, M., de Moor, M. H., & Severiens, S. E. (2026). First-year students’ sense of belonging in higher education: examining measurement invariance and longitudinal development across migration background and generation status. Studies in Higher Education, 1-22.
El Mahmoudi, A., Chaoui, N. E. H., & Chaoui, H. (2025). Predictive analytics leveraging a machine learning approach to identify students' reasons for dropping out of university. Applied Sciences, 15(15), 8496. https://doi.org/10.3390/app15158496
European Parliament. (2024). Regulation (EU) 2024/1689 of the European Parliament and of the Council laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). Official Journal of the European Union. https://digital-strategy.ec.europa.eu/en/policies/regulatory-framework-ai
Fahd, K., Venkatraman, S., Miah, S. J., & 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(3), 3743-3775. https://doi.org/10.1007/s10639-021-10741-5
Gardner, J., Yu, R., Nguyen, Q., Brooks, C., & Kizilcec, R. (2023). Cross-institutional transfer learning for educational models: Implications for model performance, fairness, and equity. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (pp. 1664-1684). ACM. https://doi.org/10.1145/3593013.3594107
Gouri, M. H., & Kumar, M. A. (2025). Automated machine learning: Empowering data-driven decisions with TPOT and Auto-sklearn. Springer.
Griep, K., Stone, L., Edwards, S., Hill, M., Cui, J., & Liu, C. (2023). Ensuring ethical, transparent, and auditable use of education data and algorithms on AutoML. In Proceedings of the 6th International Conference on Machine Learning and Natural Language Processing (pp. 66-72).
Hoca, S., & 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
Hoessly, L. (2026). On misconceptions about the Brier score in binary prediction models. Global Epidemiology, 100242.
Hurshman, C. (2024). Do opaque algorithms have functions? Synthese, 204(3), 91. https://doi.org/10.1007/s11229-024-04700-3
Ivković, R., Vučković, D., Ječmenić, M., Ananieva, D., Stanković, M., Petković, M., & Janković, N. (2025). The EU AI act and its contractual and educational implications: AI, education, and the law of obligations. International Journal of Cognitive Research in Science, Engineering and Education, 13(2), 551-562.
Khoudi, Z., Hafidi, N., Nachaoui, M., & Lyaqini, S. (2025). New approach to enhancing student performance prediction using machine learning techniques and clickstream data in virtual learning environments. SN Computer Science, 6(2), 139. https://doi.org/10.1007/s42979-025-03405-7
Kleimola, R., Hirsto, L., & Ruokamo, H. (2025). Promoting higher education students' self-regulated learning through learning analytics: A qualitative study. Education and Information Technologies, 30(4), 4959-4986. https://doi.org/10.1007/s10639-024-12996-4
Li, H., Xing, W., Li, C., Zhu, W., & Oh, H. (2025). Are simpler math stories better? Automatic readability assessment of GAI‐generated multimodal mathematical stories validated by engagement. British Journal of Educational Technology, 56(3), 1092-1117.
Lopez-Muñoz, G. L., Serrano, C. G., & Sanchez-Ferreira, C. (2026). Student Dropout Prediction in Higher Education: A Systematic Review of Machine Learning Methods and Risk Factors. Journal of Information Technology Education: Research, 25, 20.
Luo, D., Feng, C., Nong, Y., & Shen, Y. (2024). Autom3l: An automated multimodal machine learning framework with large language models. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 8586-8594). ACM. https://doi.org/10.1145/3664647.3685484
Marzouk, O. A. (2025). Benchmarking retention, progression, and graduation rates in undergraduate higher education across different time windows. Cogent Education, 12(1), 2498170. https://doi.org/10.1080/2331186X.2025.2498170
Milcu, T. (2025). Social and economic factors of academic dropout: A comprehensive analysis. Futurity of Social Sciences, 3(4), 341-353. https://doi.org/10.57125/FS.2025.12.20.14
Mnyawami, Y. N., Maziku, H. H., & Mushi, J. C. (2022). Comparative study of AutoML approach, conventional ensemble learning method, and K-Nearest Oracle-AutoML model for predicting student dropouts in Sub-Saharan African countries. Applied Artificial Intelligence, 36(1), 2145632. https://doi.org/10.1080/08839514.2022.2145632
Nawang, H., Ibrahim, N., & Yunus, F. (2025). Ensemble methods in student dropout prediction: A comprehensive review. In 2025 9th International Conference on Man-Machine Systems (ICoMMS) (pp. 42-47). IEEE.
Nigri, A., Bilancia, M., Cafarelli, B., & Magro, S. (2025). Modelling higher education dropouts using sparse and interpretable post-clustering logistic regression. arXiv preprint arXiv:2505.07582.
Olowoniyi, R., Kalita, E., & Cam, H. N. T. (2025). Dynamic dropout risk prediction in higher education: A recurrent neural network approach using longitudinal learning behavior data.
Pereira, F. D., Fonseca, S. C., Oliveira, E. H., Cristea, A. I., Bellhäuser, H., Rodrigues, L., & Carvalho, L. S. (2021). Explaining individual and collective programming students’ behavior by interpreting a black-box predictive model. IEEE Access, 9, 117097-117119.
Permana, A. E., & Santoso, E. B. (2025). Student retention early warning procedures: A case study of higher education institution management. International Journal of Economics, Business and Accounting Research (IJEBAR), 9(3). https://doi.org/10.29040/ijebar.v9i3
Persad, D., Farrell, P., & Joseph, T. (2025). Who’s Going to Leave: An Investigation of Student Attrition at a Community College in Trinidad and Tobago. Community College Journal of Research and Practice, 1-19.
Rani, S. (2025). Studying the impact of anxiety, stress, and emotion on academic performance: A systematic review. Journal of Social, Humanity, and Education, 5(2), 131-141.
Reddy, T. S. (2025). Ethical dimensions of AutoML: Addressing bias, transparency, and responsible development. Journal of Computer Science and Technology Studies, 7(5), 981-988.
Rufibach, K. (2010). Use of Brier score to assess binary predictions. Journal of Clinical Epidemiology, 63(8), 938-939. https://doi.org/10.1016/j.jclinepi.2009.11.009
Schillizzi, C. (2025). Human-centered machine learning. In Handbook of human-centered artificial intelligence (pp. 1-38). Springer Nature Singapore.
Schmidt, A., Cechinel, C., Queiroga, E. M., Primo, T., Ramos, V., & Bordin, A. S. (2025). Analyzing intervention strategies employed in response to automated academic-risk identification: A systematic review. IEEE Revista Iberoamericana de Tecnologias del Aprendizaje. https://doi.org/10.1109/RITA.2025.XXXXXXX
Schoina, C.-I., Gonida, S.-E., & Kiosseoglou, G. (2023). Dropout intentions in master studies: Applying Self-Determination Theory. Psychology: The Journal of the Hellenic Psychological Society, 28(1), 264-291. https://doi.org/10.12681/psychology.31487
Shivashankar, K., Hajj, G. S. A., & Martini, A. (2025). Scalability and maintainability challenges and solutions in machine learning: Systematic literature review. arXiv preprint arXiv:2504.11079.
Siemens, G., & Baker, R. S. D. (2012). Learning analytics and educational data mining: Towards communication and collaboration. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 252-254). ACM. https://doi.org/10.1145/2330601.2330661
Spady, W. G. (1970). Dropouts from higher education: An interdisciplinary review and synthesis. Interchange, 1(1), 64-85. https://doi.org/10.1007/BF02214313
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
Tinto, V. (2012). Leaving college: Rethinking the causes and cures of student attrition (2nd ed.). University of Chicago Press.
Tsiakmaki, M., Kostopoulos, G., Kotsiantis, S., & Ragos, O. (2019). Implementing AutoML in educational data mining for prediction tasks. Applied Sciences, 10(1), 90. https://doi.org/10.3390/app10010090
Valencia-Arias, A., Valera Aredo, J. C., Valencia, J., Cardona-Acevedo, S., Patiño-Vanegas, J. C., & Uribe Bedoya, H. (2025). Key determinants of university dropout: Academic, economic, and psychosocial factors in student retention. Frontiers in Education, 10, Article 1701644. https://doi.org/10.3389/feduc.2025.1701644
Wang, Y., Wang, H., Wang, S., Wind, S. A., & Gill, C. (2024). A systematic review and meta-analysis of self-determination-theory-based interventions in the education context. Learning and Motivation, 87, Article 102015. https://doi.org/10.1016/j.lmot.2024.102015
Weerts, H., Pfisterer, F., Feurer, M., Eggensperger, K., Bergman, E., Awad, N. (2024). Can fairness be automated? Guidelines and opportunities for fairness-aware AutoML. Journal of Artificial Intelligence Research, 79, 639-677. https://doi.org/10.1613/jair.1.14747
DOI: https://doi.org/10.32043/gsd.v10i4.1832
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 ITALIAN JOURNAL OF HEALTH EDUCATION, SPORT AND INCLUSIVE DIDACTICS
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Italian Journal of Health Education, Sports and Inclusive Didactics
Publisher: Cares srl – REN Press (since 2026). Previously published by Gaia srl – Edizioni Universitarie Romane (2017–2025).
ISSN: 2532-3296 E-ISSN: 3103-5744