Have a personal or library account? Click to login
Early Identification of At-Risk Students in Online Education: A Deep Learning Approach to Predictive Modelling Cover

Early Identification of At-Risk Students in Online Education: A Deep Learning Approach to Predictive Modelling

Open Access
|Dec 2025

Abstract

Background

Predicting student performance in online learning is difficult due to class imbalance and limited model interpretability. At-risk students are fewer than high performers, biasing predictions, and methods like SMOTE fail to preserve temporal patterns. Although black-box models are accurate, they lack transparency for actionable insights.

Objectives

This study proposes a deep learning framework combining LSTM networks and attention mechanisms to address these issues using the OULAD dataset. LSTMs capture temporal dependencies, while attention improves interpretability by emphasising key features. Advanced resampling mitigates class imbalance for robust at-risk student detection.

Methods/Approach

The methodology applies the KDD framework to process data, uncover patterns, and build models that predict student success risk, ensuring efficient data handling, robust modelling, and actionable insights to improve retention.

Results

The BiLSTM-RNN achieved the best performance, effectively capturing temporal dependencies and attaining the highest accuracy, precision, recall, and F1-score.

Conclusions

The findings support more effective and targeted interventions in online education, offering valuable insights for research and practice.

DOI: https://doi.org/10.2478/bsrj-2025-0019 | Journal eISSN: 1847-9375 | Journal ISSN: 1847-8344
Language: English
Page range: 69 - 91
Submitted on: Jan 14, 2025
|
Accepted on: Aug 15, 2025
|
Published on: Dec 21, 2025
In partnership with: Paradigm Publishing Services
Publication frequency: 2 issues per year

© 2025 Lediana Shala Riza, Lejla Abazi Bexheti, Jovana Zoroja, published by IRENET - Society for Advancing Innovation and Research in Economy
This work is licensed under the Creative Commons Attribution 4.0 License.