Predicting JNTUA CEA Student's Academic Performance Using Deep Neural Networks

Beginning of any graduate program, how to forecast learners' academic progress is a widely research topic in the field of educational data mining (EDM). Students encounter a variety of difficulties in undergraduate programs, which contributes to high failure and dropout rates. To predict learners' success rates, EDMis employed to analyze student data gathered from different educational contexts. The proposed predictive model used a Deep Neural Network (DNN) for training and testing datasets. In this project, a dataset from Jawaharlal Nehru Technological University Anantapur College of Engineering Anantapur (JNTUA CEA) is taken to foretell the student's performance. Deep Artificial Neural Network (DANN) can be used to forecast based on their scores from former courses, students' academic success in subsequent courses. Comparing the proposed approach to existing models, the present study achieved a 96 % of accuracy rate.