Analysis of Learning Factors and Academic Performance of Non-Elite Students Using Machine Learning Models

Guangda Yang, Hongfei Zhang, Yongjiao Pang, Suning Luo
Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, PMLR 278:313-321, 2025.

Abstract

This study applies machine learning models, including logistic regression, random forest, support vector machine (SVM), and XGBoost, to analyze and predict the final grades of non-elite university science students. The data includes attendance, note-taking scores, homework scores, quiz scores, and screen-cutting behavior. The results indicate that quiz scores, homework scores, and note-taking scores are the key factors for predicting final grades, with a particular impact from mid-term and pre-final quiz scores. SVM performs well in predicting students at risk of failing, while random forest and XGBoost show stronger stability in handling complex data. Analysis of the importance analysis reveals that students’ engagement, such as quiz and homework scores, is strongly correlated with final grades. The findings suggest that machine learning can effectively identify students at academic risk, providing data support for educational interventions. Future research could integrate more student behavior data and sentiment analysis to further improve prediction accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v278-yang25c, title = {Analysis of Learning Factors and Academic Performance of Non-Elite Students Using Machine Learning Models}, author = {Yang, Guangda and Zhang, Hongfei and Pang, Yongjiao and Luo, Suning}, booktitle = {Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing}, pages = {313--321}, year = {2025}, editor = {Zeng, Nianyin and Pachori, Ram Bilas and Wang, Dongshu}, volume = {278}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v278/main/assets/yang25c/yang25c.pdf}, url = {https://proceedings.mlr.press/v278/yang25c.html}, abstract = {This study applies machine learning models, including logistic regression, random forest, support vector machine (SVM), and XGBoost, to analyze and predict the final grades of non-elite university science students. The data includes attendance, note-taking scores, homework scores, quiz scores, and screen-cutting behavior. The results indicate that quiz scores, homework scores, and note-taking scores are the key factors for predicting final grades, with a particular impact from mid-term and pre-final quiz scores. SVM performs well in predicting students at risk of failing, while random forest and XGBoost show stronger stability in handling complex data. Analysis of the importance analysis reveals that students’ engagement, such as quiz and homework scores, is strongly correlated with final grades. The findings suggest that machine learning can effectively identify students at academic risk, providing data support for educational interventions. Future research could integrate more student behavior data and sentiment analysis to further improve prediction accuracy.} }
Endnote
%0 Conference Paper %T Analysis of Learning Factors and Academic Performance of Non-Elite Students Using Machine Learning Models %A Guangda Yang %A Hongfei Zhang %A Yongjiao Pang %A Suning Luo %B Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2025 %E Nianyin Zeng %E Ram Bilas Pachori %E Dongshu Wang %F pmlr-v278-yang25c %I PMLR %P 313--321 %U https://proceedings.mlr.press/v278/yang25c.html %V 278 %X This study applies machine learning models, including logistic regression, random forest, support vector machine (SVM), and XGBoost, to analyze and predict the final grades of non-elite university science students. The data includes attendance, note-taking scores, homework scores, quiz scores, and screen-cutting behavior. The results indicate that quiz scores, homework scores, and note-taking scores are the key factors for predicting final grades, with a particular impact from mid-term and pre-final quiz scores. SVM performs well in predicting students at risk of failing, while random forest and XGBoost show stronger stability in handling complex data. Analysis of the importance analysis reveals that students’ engagement, such as quiz and homework scores, is strongly correlated with final grades. The findings suggest that machine learning can effectively identify students at academic risk, providing data support for educational interventions. Future research could integrate more student behavior data and sentiment analysis to further improve prediction accuracy.
APA
Yang, G., Zhang, H., Pang, Y. & Luo, S.. (2025). Analysis of Learning Factors and Academic Performance of Non-Elite Students Using Machine Learning Models. Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 278:313-321 Available from https://proceedings.mlr.press/v278/yang25c.html.

Related Material