A Stacking-Based RF-CatBoost Model for Student Performance Prediction
ICCK Transactions on Educational Data Mining · 2025
DOI: 10.62762/tedm.2025.397583 ↗Kurz gefasst
Fachartikel in der Zeitschrift ICCK Transactions on Educational Data Mining, 2025. Verfasst von Jing Zhao.
Abstract (Originalsprache)
To address the student performance problem in educational data mining, this study proposes a stacking-based RF-CatBoost model that integrates the complementary strengths of ensemble learning methods to enhance prediction accuracy and robustness. In the proposed framework, Random Forest (RF) and CatBoost are employed as the base learners to capture both global feature interactions and complex non-linear relationships within multi-source educational data. Their outputs are then stacked and fused using a combination strategy to generate the final prediction. Experimental results based on two educational datasets demonstrate that the stacking-based RF-CatBoost model consistently achieves superior predictive performance, reflected in prediction accuracy and robustness. The results confirm that the proposed hybrid stacking RF-CatBoost can effectively leverage the diversity of ensemble learners, offering a robust solution for early student performance prediction, enabling timely interventions and personalized learning support in educational setting.
Zitieren
APA
Zhao, J. (2025). A Stacking-Based RF-CatBoost Model for Student Performance Prediction. ICCK Transactions on Educational Data Mining. https://doi.org/10.62762/tedm.2025.397583
Vancouver
Zhao J. A Stacking-Based RF-CatBoost Model for Student Performance Prediction. ICCK Transactions on Educational Data Mining. 2025. doi:10.62762/tedm.2025.397583
BibTeX
@article{Zhao2025,
author = {Zhao, Jing},
title = {A Stacking-Based RF-CatBoost Model for Student Performance Prediction},
journal = {ICCK Transactions on Educational Data Mining},
year = {2025},
doi = {10.62762/tedm.2025.397583}
}
EUVIMED