Table 1.
Literature review on predicting academic achievement.
Fig 1.
Proposed framework.
Fig 2.
Dataset attributes (Abstract view).
Table 2.
Description of data files.
Fig 3.
Random forest feature importance.
Fig 4.
Proposed DBTM architecture of data flow.
Fig 5.
Parameter tuning process.
Fig 6.
Performance metrics.
Fig 7.
Distribution of dataset (Assessment score).
Fig 8.
Activity types and final result.
Fig 9.
Distribution of dataset (Relation between score and VLE).
Fig 10.
Numeric attributes correlation.
Table 3.
Analyzing the new method’s performance in contrast to the current one.
Table 4.
Statistical analysis results on the OULAD dataset.
Fig 11.
Sensitivity study to determine how factors affect model performance.
Fig 12.
Connection between data amount and duration of execution.