Learning Analytics for Early Identification of At-Risk Students
US Journal of New Insights in Tech & Education · 25.07.2023
DOI: 10.69013/fd2910sc ↗Kurz gefasst
Fachartikel in der Zeitschrift US Journal of New Insights in Tech & Education, online erschienen am 25.07.2023. Verfasst von Ashraful Islam Albi und 1 weiteren Autor:innen. Die Arbeit nennt 7 Literaturangaben.
Abstract (Originalsprache)
Identifying students at risk of academic failure early enough to intervene is a central goal of learning analytics and educational data mining (EDM). This paper reports an empirical machine learning study built on the widely used UCI Student Performance dataset (Cortez & Silva, 2008; N = 395 secondary school students). An at-risk indicator was defined as a final grade below 10 out of 20, and three supervised classifiers, logistic regression, random forest, and gradient boosting, were trained on an early-warning feature set consisting of demographic, socio-behavioral, and first-period academic indicators, deliberately excluding later-period grades to preserve genuine early-prediction validity. All three models achieved strong discrimination (area under the receiver operating characteristic curve, AUC, between 0.910 and 0.912), with gradient boosting achieving the best balance of precision and recall (F1 = 0.771) on a held-out test set. First-period grade, prior course failures, and absenteeism emerged as the dominant predictors of at-risk status. The paper situates these results within the broader learning analytics literature on early-warning systems and discusses the implications, limitations, and ethical considerations of deploying such models to trigger institutional support for at-risk students.
Zitieren
APA
Albi, A. I., & Bhattacharjee, A. (2023). Learning Analytics for Early Identification of At-Risk Students. US Journal of New Insights in Tech & Education. https://doi.org/10.69013/fd2910sc
Vancouver
Albi AI, Bhattacharjee A. Learning Analytics for Early Identification of At-Risk Students. US Journal of New Insights in Tech & Education. 2023. doi:10.69013/fd2910sc
BibTeX
@article{Albi2023,
author = {Albi, Ashraful Islam and Bhattacharjee, Ashok},
title = {Learning Analytics for Early Identification of At-Risk Students},
journal = {US Journal of New Insights in Tech & Education},
year = {2023},
doi = {10.69013/fd2910sc}
}
EUVIMED