Machine Learning and Deep Learning based Students’ Grades Prediction

Abstract

Abstract Predicting student performance in a curriculum or program offers the prospect of improving academic outcomes. By using effective performance prediction methods, instructional leaders can allocate adequate resources and instruction more accurately. This paper aims to identify the features of machine learning algorithms that can be used to make predictions about student grades. For this purpose, we use a data set that contains personal information about students and their grades. We have implemented different machine learning algorithms of regression namely: Decision Tree, Random Forest, Linear Regression, k-Nearest Neighbor, XGBoost, and Deep Neural Network. Then, we compared these models based on their determination coefficient, Mean Average Error, Mean Squared Error, and Root Mean Squared Error. The experimental results of this study showed that the deep neural network outperformed the other algorithms with a determination coefficient of 99.97% and low errors.