Treffer: A machine learning based model for student's dropout prediction in online training.

School dropout is a significant issue in distance learning, and early detection is crucial for addressing the problem. Our study aims to create a binary classification model that anticipates students' activity levels based on their current achievements and engagement on a Canadian Distance learning Platform. Predicting student dropout, a common classification problem in educational data analysis, is addressed by utilizing a comprehensive dataset that includes 49 features ranging from socio-demographic to behavioral data. This dataset provides a unique opportunity to analyze student interactions and success factors in a distance learning environment. We have developed a student profiling system and implemented a predictive approach using XGBoost, selecting the most important features for the prediction process. In this work, our methodology was developed in Python, using the widely used sci-kit-learn package. Alongside XGBoost, logistic regression was also employed as part of our combination of strategies to enhance the models predictive capabilities. Our work can accurately predict student dropout, achieving an accuracy rate of approximately 82% on unseen data from the next academic year. [ABSTRACT FROM AUTHOR]

Copyright of Education & Information Technologies is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)