TY  - JOUR
AU  - Weng, Shaoyuan
AU  - Liu, Zimeng
AU  - Zheng, Yuanyuan
AU  - Zhang, Chao
PY  - 2025
DA  - 2025/11/22
TI  - A Jellyfish Search Optimizer-Based Optimization Framework for Student Performance Prediction
JO  - ICCK Transactions on Educational Data Mining
T2  - ICCK Transactions on Educational Data Mining
JF  - ICCK Transactions on Educational Data Mining
VL  - 1
IS  - 1
SP  - 6
EP  - 15
DO  - 10.62762/TEDM.2025.736642
UR  - https://www.icck.org/article/abs/TEDM.2025.736642
KW  - automatic parameter optimization
KW  - jellyfish search optimizer
KW  - student performance prediction
KW  - educational data mining
AB  - 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 significantly enhances the performance of baseline models across all evaluated metrics. Leveraging this superior performance, the framework provides a robust tool for student performance prediction and a wide array of educational analytics applications.
SN  - 3070-5843
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Weng2025A,
  author = {Shaoyuan Weng and Zimeng Liu and Yuanyuan Zheng and Chao Zhang},
  title = {A Jellyfish Search Optimizer-Based Optimization Framework for Student Performance Prediction},
  journal = {ICCK Transactions on Educational Data Mining},
  year = {2025},
  volume = {1},
  number = {1},
  pages = {6-15},
  doi = {10.62762/TEDM.2025.736642},
  url = {https://www.icck.org/article/abs/TEDM.2025.736642},
  abstract = {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 significantly enhances the performance of baseline models across all evaluated metrics. Leveraging this superior performance, the framework provides a robust tool for student performance prediction and a wide array of educational analytics applications.},
  keywords = {automatic parameter optimization, jellyfish search optimizer, student performance prediction, educational data mining},
  issn = {3070-5843},
  publisher = {Institute of Central Computation and Knowledge}
}