What question did this study set out to answer?

This study aims to investigate the use of graph neural networks to model student academic progression across different faculties.

June 6, 2026Applied SciencesOpen Access

Academic Trajectory Graphs for Temporal Modelling of Student Academic Progression

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates predictive performance of graph models in academic progression, suggesting enhanced insights for diverse academic paths.

This study aims to investigate the use of graph neural networks to model student academic progression across different faculties.
Evaluated graph-based approaches including DGCNN, GCN, and node2vec in comparison to conventional models.
Used semester-to-semester course transitions to establish Academic Trajectory Graphs (ATGs).
Utilized AUC, accuracy, and F1-scores as evaluation metrics for model performance.
DGCNN achieved AUC values up to 0.988 and accuracy up to 0.945 across faculties.
Conventional models demonstrated strongest overall predictive performance with aggregated indicators.
Graph-based trajectory models preserved unique temporal and relational information not captured in traditional models.

Ahmed et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

June 6, 2026Applied SciencesOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates predictive performance of graph models in academic progression, suggesting enhanced insights for diverse academic paths.

This study aims to investigate the use of graph neural networks to model student academic progression across different faculties.
Evaluated graph-based approaches including DGCNN, GCN, and node2vec in comparison to conventional models.
Used semester-to-semester course transitions to establish Academic Trajectory Graphs (ATGs).
Utilized AUC, accuracy, and F1-scores as evaluation metrics for model performance.
DGCNN achieved AUC values up to 0.988 and accuracy up to 0.945 across faculties.
Conventional models demonstrated strongest overall predictive performance with aggregated indicators.
Graph-based trajectory models preserved unique temporal and relational information not captured in traditional models.

Ahmed et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark