engleski

Early prediction of student performance in massive open online courses at different stages of course progress

Student success is paramount at all levels of education, especially for universities. Improving the success and quality of enrolled students is one of the most important concerns. It is important to monitor the early symptoms of at-risk students and take preventive measures earlier to identify the cause of student dropout rate. In this research, we will use data mining techniques to identify the factors that influence student success. We use the Open University Learning Analytics Dataset (OULAD) education dataset code module FFF and code presentation 2014J with 2364 students. We used grid search along with ANOVA ranked feature combinations in a pipeline to build our model. In this context, we will use Logistic Regression and Decision Tree for classification models. This research focuses on evaluating how predictions change over time after each test and how early we can obtain good predictive power. We built the model immediately after each exam in the course. The results showed that we can get good results very early in the course, which gives much more room for timely intervention.

machine learning ; decision tree ; student performance ; OULAD dataset

nije evidentirano