A Comparative Analysis for GPA Prediction of Undergraduate Students Using Machine and Deep Learning

Abstract

Recently the research field of machine learning has experienced a huge rise in popularity and growth. Machine Learning (ML) is a way of improving computational prediction models by allowing the computer to generate its own algorithm to predict outcomes, based on an existing dataset. In this paper, we demonstrate the application of Machine Learning to enhance the educational processes. We implemented regression and supervised learning techniques on data from King Saud University, Riyadh, Saudi Arabia, to construct a predictive model for student performance. This allows for timely interventions in students' academic paths. We utilized extensive and diverse course records, encompassing several academic years and programs, to conduct a comparative analysis of various Machine and Deep Learning methodologies, assessing their efficacy through performance metrics. The developed ML/DL algorithms use Grade Point Averages (GPAs) of courses and semesters as explanatory features to predict the student’s final GPA, which is the target value of the models. Based on the results, the linear and bagging regression models have the best Mean Absolute Error (MAE) performance metric. To ensure there will be enough time for academic intervention, data of early courses and semesters are used.