Ensemble Learning for Dropout Forecasting in Higher Education: A Layered Generalization Method

DOI

10.2991/978-94-6463-926-1_51How to use a DOI?

Keywords

Dropout Forecasting; Ensemble Learning; Prediction Model

Abstract

This research highlights the problem of dropout at the university level as a global issue that has a wide impact, not only on individuals but also on institutions, families, and communities. With technological advancements, big data is now used to analyze and predict the risk of dropping out of school more accurately. The study introduces an ensemble stacking approach that combines Random Forest (RF), Extreme Gradient Boosting (XGBoost), Gradient Boosting (GB), and Feed-forward Neural Networks (FNN) to predict students at risk of dropping out based on data that includes demographic, socio-economic, and academic perfor-mance factors. Different from previous studies that only focused on a specific level or discipline, this approach was tested on data from various majors such as agronomy, design, education, nursing, journalism, management, social services, and technology. The results show that this model is more accurate than conven-tional prediction models, indicated by higher accuracy values and AUC. These findings allow educational institutions to identify at-risk students early and im-plement preventive interventions to improve student retention and academic success.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Norma Puspitasari
AU  - Mochamad Agung Wibowo
AU  - Budi Warsito
PY  - 2025
DA  - 2025/12/31
TI  - Ensemble Learning for Dropout Forecasting in Higher Education: A Layered Generalization Method
BT  - Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2025 (iCAST-ES 2025)
PB  - Atlantis Press
SP  - 450
EP  - 458
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-926-1_51
DO  - 10.2991/978-94-6463-926-1_51
ID  - Puspitasari2025
ER  -