Deep regressor: Cross subject academic performance prediction system for university level students

Abstract

Predicting the academic performance of students has been an important research topic in the Educational field. The main aim of a higher education institution is to provide quality education for students. One way to accomplish a higher level of quality of education is by predicting student’s academic performance and there by taking earlyre-medial actions to improve the same. This paper presents a system which utilizes machine learning techniques to classify and predict the academic performance of the students at the right time before the drop out occurs. The system first accepts the performance parameters of the basic level courses which the student had already passed as these parameters also influence the further study. To pre-dict the performance of the current program, the system continuously accepts the academic performance parame-ters after each academic evaluation process. The system employs machine learning techniques to study the aca-demic performance of the students after each evaluation process. The system also learns the basic rules followed by the University for assessing the students. Based on the present performance of the students, the system classifies the students into different levels and identify the students at high risk. Earlier prediction can help the students to adopt suitable measures in advance to improve the per for-man ce. The systems can also identify the factor saffecting the performance of the same students which helps them to take remedial measures in advance.