A Convolutional Neural Network Framework for Predicting Student Drop Out in Universities

The phenomenon of student attrition is common in almost all universities if not all over the world and its effects are felt at several levels be it at society level or the personal level of students who abandon the university and so forth. Most implemented machine learning frameworks for predicating university student drop-out have data validation points limitations which are not hyper-tuned from datasets used thereby not providing accurate predication of likelihood for student dropouts. Therefore, this research developed a convolutional neural network framework that predicts student attrition in relation to influential factors. The study employed a rigorous methodology to collect and preprocess data from a diverse set of universities, which was then used to train and test the CNN model. The model's performance was evaluated using various metrics, including accuracy, precision, and recall, to ensure its robustness and effectiveness in predicting student dropouts. The findings of this study can serve as a valuable resource for future research in this area.