TY  - JOUR
AU  - Wang, Chenxi
AU  - Yao, Shuilin
PY  - 2025
DA  - 2025/12/25
TI  - Enhancing Student Dropout and Academic Success Prediction Using Machine Learning and Over-sampling Techniques
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  - 36
EP  - 43
DO  - 10.62762/TEDM.2025.732573
UR  - https://www.icck.org/article/abs/TEDM.2025.732573
KW  - student dropout prediction
KW  - over-sampling
KW  - SMOTE
KW  - ADASYN
KW  - academic success
AB  - Predicting student dropout and academic success is important for higher education institutions for enhancing retention and deliver timely interventions. However, educational datasets often exhibit severe class imbalance, particularly when multiple academic outcomes (i.e., dropout, enrolled, and graduate) are considered simultaneously. Thus this study examines the effectiveness of three widely used over-sampling techniques (i.e., RandomOverSampler, synthetic minority oversampling technique, and adaptive synthetic sampling) for mitigating class imbalance and enhancing prediction performance. These sampling strategies are evaluated in combination with several machine learning classifiers to assess their influence on accuracy of minority-class detection. The experimental results show that appropriate over-sampling substantially improves model performance, especially for the minority categories. The findings highlight the critical role of imbalance-handling techniques in educational data mining and offer practical insights for institutions seeking to build robust early-warning systems.
SN  - 3070-5843
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Wang2025Enhancing,
  author = {Chenxi Wang and Shuilin Yao},
  title = {Enhancing Student Dropout and Academic Success Prediction Using Machine Learning and Over-sampling Techniques},
  journal = {ICCK Transactions on Educational Data Mining},
  year = {2025},
  volume = {1},
  number = {1},
  pages = {36-43},
  doi = {10.62762/TEDM.2025.732573},
  url = {https://www.icck.org/article/abs/TEDM.2025.732573},
  abstract = {Predicting student dropout and academic success is important for higher education institutions for enhancing retention and deliver timely interventions. However, educational datasets often exhibit severe class imbalance, particularly when multiple academic outcomes (i.e., dropout, enrolled, and graduate) are considered simultaneously. Thus this study examines the effectiveness of three widely used over-sampling techniques (i.e., RandomOverSampler, synthetic minority oversampling technique, and adaptive synthetic sampling) for mitigating class imbalance and enhancing prediction performance. These sampling strategies are evaluated in combination with several machine learning classifiers to assess their influence on accuracy of minority-class detection. The experimental results show that appropriate over-sampling substantially improves model performance, especially for the minority categories. The findings highlight the critical role of imbalance-handling techniques in educational data mining and offer practical insights for institutions seeking to build robust early-warning systems.},
  keywords = {student dropout prediction, over-sampling, SMOTE, ADASYN, academic success},
  issn = {3070-5843},
  publisher = {Institute of Central Computation and Knowledge}
}