| Popis: |
In recent years, predicting student’s academic performance is the main objective of all educational institutions. Numerous research works show that machine learning can be a highly efficient technology to meet this objective. In this research work, our first purpose is to compare several machine learning algorithms for predicting students’ academic performance. The machine learning algorithms used for comparison are ANCOVA, Logistic Regression, Support Vector Regression, Log-linear Regression, Decision Tree Regression, Random Forest Regression, and Partial Least Squares Regression. Our second purpose is to evaluate the seven algorithms used using the various evaluation metrics. The experimental results showed that the Log-linear Regression provides a better prediction, closely followed by ANCOVA. |
