EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning Analytics for Predicting Student Performance in Online Learning Environments

Sayed Mahbub Hasan Amiri

Journal of Research, Innovation, and Strategies for Education (RISE) · 05.08.2026 · 3 (4) · 172-201

DOI: 10.70148/rise.v3i4.11 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Research, Innovation, and Strategies for Education (RISE), online erschienen am 05.08.2026. Verfasst von Sayed Mahbub Hasan Amiri. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The fast‑growing numbers of the online learning space have led to the storage of huge amounts of student interaction data in Learning Management Systems (LMS). However, educational institutions often lack systematic systems to use such data to help identify students who are at risk of future academic failure. This paper fills this gap by building and testing predictive models to predict academic performance of students through learning analytics. Using a quantitative research design, we studied the interaction logs, assessment data, and recorded engagement of 384 university students taking a semester‑long online course through Moodle. The most essential behavioral variables, such as the number of logins, the timeliness of assignment submissions, discussion forum activity, and video lecture viewing, were extracted and were used to train and compare various machine learning models, namely, Logistic Regression, Decision Tree [added: now includes Decision Tree as in results], Random Forest, and Support Vector Machine. Accuracy, precision, recall, F1‑score, and ROC‑AUC were used to measure model performance. Findings indicate that the highest predictive accuracy was achieved by Random Forest (87.0%), with an ROC‑AUC of 0.91, and the assignment submission pattern and regular login frequency were the most potent predictors of ultimate academic achievement. These findings highlight the possibility of learning analytics to support early warning systems based on data, enabling timely pedagogical interventions. This paper contributes to the literature on educational data mining through empirical evidence of the relationships between behavioral indicators derived from conventional LMS logs and their strong predictive abilities for student results, providing practical implications for instructors, instructional designers, and institutional policymakers seeking to enhance student learning and tailor support in online learning settings.

Zitieren

APA

Amiri, S. M. H. (2026). Learning Analytics for Predicting Student Performance in Online Learning Environments. Journal of Research, Innovation, and Strategies for Education (RISE), 3(4), 172-201. https://doi.org/10.70148/rise.v3i4.11

Vancouver

Amiri SMH. Learning Analytics for Predicting Student Performance in Online Learning Environments. Journal of Research, Innovation, and Strategies for Education (RISE). 2026;3(4):172-201. doi:10.70148/rise.v3i4.11

BibTeX
@article{Amiri2026,
  author = {Amiri, Sayed Mahbub Hasan},
  title = {Learning Analytics for Predicting Student Performance in Online Learning Environments},
  journal = {Journal of Research, Innovation, and Strategies for Education (RISE)},
  year = {2026},
  volume = {3},
  number = {4},
  pages = {172--201},
  doi = {10.70148/rise.v3i4.11}
}
Kostenlos starten →