Treffer: Predictive Analytics for Student Online Learning Performance Using Machine Learning and Data Mining Techniques.

Machine learning and data mining techniques have been widely used in online educational settings to identify the important features that tend to influence students' learning performance and predict their future performance. However, there is little to no research done in the context of Singapore's education. Hence, this study aims to fill the gap by developing an early detection model for weaker students using various machine learning techniques and investigate potential factors that may affect students' learning performance. All the data analysis and model development are done using Python. Firstly, exploratory data analysis is performed to analyse the dataset. Secondly, data pre-processing and feature engineeritlg were performed. Next. three models were developed using decision tree, random forest, and neural network. The performance of the developed models was then evaluated. From our analysis, we found that neural network achieved the highest accuracy of 74.46%. From the confusion matrix, most of the values are within or near the matrix diagonal, indicating that the model is a good fit. Further model improvements could also be done, such as pruning of the decision trees, or the use of ensemble models such as soft voting classifiers to prevent overfitting and improve overall accuracy. [ABSTRACT FROM AUTHOR]

Copyright of International Journal on E-Learning is the property of Association for the Advancement of Computing in Education 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.)