Aggregating Time Series and Tabular Data in Deep Learning Model for University Students’ GPA Prediction

Current approaches of university students' Grade Point Average (GPA) prediction rely on the use tabular data as input. Intuitively, adding historical GPA can help to improve performance a model. In this study, we present dual-input deep learning model that is able simultaneously process time-series and for predicting student GPA. Our proposed achieved best among all tested models with 0.4142 MSE (Mean Squared Error) 0.418 MAE Absolute 4.0 scale. It also has R 2 -score 0.4879, which means it explains true distribution better than other models.