Unveiling Accuracy-Fairness Trade-Offs
Journal of Learning Analytics · 31.07.2025 · 12 (2) · 125-139
DOI: 10.18608/jla.2025.8543 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Learning Analytics, online erschienen am 31.07.2025. Verfasst von Raymond A. Opoku und 2 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
While high-accuracy machine learning (ML) models for predicting student learning performance have been widely explored, their deployment in real educational settings can lead to unintended harm if the predictions are biased. This study systematically examines the trade-offs between prediction accuracy and fairness in ML models trained on the widely used Open University Learning Analytics Dataset (OULAD). We evaluated the relationship between model accuracy and fairness across various student demographic subgroups and investigated the extent to which fairness can be improved without significantly sacrificing accuracy. Our analysis revealed that standard ML models often exhibit bias; however, applying bias mitigation techniques can reduce these disparities while maintaining acceptable accuracy. Our findings emphasize the importance of auditing ML models for fairness to ensure that predictive insights are equitable across diverse student populations. We also discuss implications for best practices and challenges in achieving fair ML models for student performance prediction.
Zitieren
APA
Opoku, R. A., Pei, B., & Xing, W. (2025). Unveiling Accuracy-Fairness Trade-Offs. Journal of Learning Analytics, 12(2), 125-139. https://doi.org/10.18608/jla.2025.8543
Vancouver
Opoku RA, Pei B, Xing W. Unveiling Accuracy-Fairness Trade-Offs. Journal of Learning Analytics. 2025;12(2):125-139. doi:10.18608/jla.2025.8543
BibTeX
@article{Opoku2025,
author = {Opoku, Raymond A. and Pei, Bo and Xing, Wanli},
title = {Unveiling Accuracy-Fairness Trade-Offs},
journal = {Journal of Learning Analytics},
year = {2025},
volume = {12},
number = {2},
pages = {125--139},
doi = {10.18608/jla.2025.8543}
}
EUVIMED