Early Warning System for Academic using Data Mining

Nowadays, student academic data in universities are very huge. However, the opportunity to manage the data is a knowledge that cannot be overlooked. Educational data mining is a current research field which uses data mining algorithms to transform large volumes of academic data into valuable knowledge capable of improving the educational processes and decisions. This research makes use of a set of three models. The first two models used the data obtained in the first year (first semester and second semester), to predict the academic success of the enrolled students, while the third model used the information available at the end of the first year to predict the academic performances of the students at the end of their study. At the same time, this work also intends to identify the factors that are most critical to these models. The results of this research paved way for the head of the school to identify students in need of more pedagogical support, as well as students with high probability of excelling in their studies. It could also allow them to focus their attention on the critical aspects, by implementing mechanisms that tackles students' difficulties.