Machine Learning Methods for Predicting Student Academic Performance Using Behavioral Data
International Journal of Drug Delivery Technology · 19.06.2026 · 16 (56s)
DOI: 10.25258/ijddt.16.56s.72 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 19.06.2026. Verfasst von Manali Gupta und 6 weiteren Autor:innen.
Abstract (Originalsprache)
With the proliferation of digital learning platforms and educational technologies, the amount of data generated and available to decision makers in education has also grown exponentially, offering the potential to enhance academic decision making and student learning outcomes. The main objective of the research is to explore the use of machine learning techniques for predicting the academic performance of students based on behavioral data. The emphasis of the study is to examine the behaviour indicators based on attendance, participation in the classroom, submission of assignments, participation in discussions and participation in online learning activities and their influence on academic achievement. In this work, some of the supervised machine learning algorithms such as Decision Tree, Logistic Regression, Naive Bayes, Support Vector Machine (SVM), Random Forest, and XGBoost were used and tested with the educational datasets. To optimize the model performance and classification accuracy, data preprocessing methods like normalization, encoding and feature selection were used. The experimental results showed that ensemble learning algorithms outperform the traditional classification. XGBoost (93.4%) and Random Forest (91.6%) were the two models with the highest prediction accuracy among those evaluated. Results suggest that reliability of prediction is improved when behavioral data is incorporated and that it is helpful for early identification of academically at-risk students. The suggested predictive system can help educational institutions adopt personalized learning strategies, academic advising, and timely intervention systems. This study has implications for the field of educational data mining, showing how well machine learning methods can be used to analyze student behavior and enhance academic performance prediction systems.
Zitieren
APA
Gupta, M., Arora, S., Rao, P., Rajendra, K. B., Lodhi, S. S., Kumar, S., & Baghel, S. (2026). Machine Learning Methods for Predicting Student Academic Performance Using Behavioral Data. International Journal of Drug Delivery Technology, 16(56s). https://doi.org/10.25258/ijddt.16.56s.72
Vancouver
Gupta M, Arora S, Rao P, Rajendra KB, Lodhi SS, Kumar S, et al. Machine Learning Methods for Predicting Student Academic Performance Using Behavioral Data. International Journal of Drug Delivery Technology. 2026;16(56s). doi:10.25258/ijddt.16.56s.72
BibTeX
@article{Gupta2026,
author = {Gupta, Manali and Arora, Sonia and Rao, Prakriti and Rajendra, Kanojiya Babalu and Lodhi, Samta Suman and Kumar, Saurabh and Baghel, Shivangi},
title = {Machine Learning Methods for Predicting Student Academic Performance Using Behavioral Data},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {56s},
doi = {10.25258/ijddt.16.56s.72}
}
EUVIMED