Student performance prediction using Support Vector Machine and K-Nearest Neighbor

This work presented two prediction models for the estimation of student's performance in final examination. The work made use of the popular dataset provided by the University of Minho in Portugal, which relate to the performance in math subject and it consists of 395 data samples. Forecasting the performance of students can be useful in taking early precautions, instant actions, or selecting a student that is fit for a certain task. The need to explore better models to achieve better performance cannot be overemphasized. Most of earlier work on the same dataset used K-Nearest Neighbor algorithm and achieved low results, while Support Vector Machine algorithm was rarely used, which happens to be a very popular and powerful prediction technique. To ensure better comparison, we applied both Support Vector Machine algorithm and K-Nearest Neighbor algorithm on the dataset to predict the student's grade and then compared their accuracy. Empirical studies outcome indicated that Support Vector Machine achieved slightly better results with correlation coefficient of 0.96, while the K-Nearest Neighbor achieved correlation coefficient of 0.95.