In educational data mining, accurate prediction of student performance is important for supporting timely intervention for at-risk students. However, educational datasets often include irrelevant or redundant features that could reduce the performance of prediction models. To tackle this issue, this study proposes a gradient boosting-based feature selection framework that can automatically identify and obtain the most important features for student performance prediction. The proposed framework leverages the gradient boosting model to calculate feature importance and refine the feature subset, aiming to achieve comparable or superior prediction performance using fewer but important input fea... More >

Student performance prediction represents a core task in educational data mining, facilitating early interventions, personalized learning support, and data-driven decision-making. While machine learning models have demonstrated strong predictive capabilities in this domain, their effectiveness remains constrained by hyperparameter selection. To overcome this limitation, we introduce an automated hyperparameter optimization framework that leverages the jellyfish search optimizer to identify optimal configurations. To mitigate the variability introduced by data partitioning, we adopt 10-fold cross-validation with 10 repeated trials. Experimental results indicate that the proposed framework sig... More >