Improving Students Performance Using Data Clustering and Neural Networks in Foreign-Language Based Higher Education

The academic performance of engineering and science students during their first year at university is a turning point in their educational path and usually encroaches on their General Point Average (GPA) in a decisive manner. A case of particular interest is when students have to learn their courses materials in a foreign language. Indeed, it usually cumulates an additional handicap as will be shown. In this paper, we present a hybrid procedure based on Neural Networks (NN) and Data Clustering that enables academicians to predict students GPA according to their foreign language performance at a first stage, then classify the student in a well-defined cluster for further advising and follow up by forming a new system entry. This procedure has mainly a twofold objective. It allows meticulous advising during registration and thus, helps maintain high retention rate, acceptable GPA and grant management. Additionally, it endows instructors an anticipated estimation of their students capabilities during team forming and in-class participation. The results demonstrated a high level of accuracy and efficiency in identifying slow, moderate and fast learners and in endowing advisors as well as instructors an efficient tool in tackling this specific aspect of the learners academic standards and path.