Predicting Pre-university Student's Mathematics Achievement

This study exploits three methods, namely the Back-propagation Neural Network (BPNN), Classification and Regression Tree (CART), and Generalized Regression Neural Network (GRNN) in predicting the student's mathematics achievement. The first part of this study utilizes enrolment data to predict the student's mid-semester evaluation result, whereas the latter part employs additional data to predict the student's final examination result. The predictive model's accuracy is evaluated using 10-fold cross-validation to identify the best model. The findings reveal that BPNN outperforms other models with an accuracy of 66.67% and 71.11% in predicting the mid-semester evaluation result and the final examination result respectively.