Evaluating Performance and Dropouts of Undergraduates Using Educational Data Mining

Undergraduate students have different levels of motivation, different attitudes about learning, and different responses to specific instructional practices. Predicting the academic performance of students is an issue faced by many universities in emerging countries. Although those institutions store large amounts of educational data they are unsuccessful to detect which students are at risk of leaving the educational system. This paper presents an architecture that uses educational data mining techniques to predict and identify those who face the risk of dropping out. The approach may assist educational managers in supervising the development of students at the end of each academic term, identifying the ones with difficulties to fulfill their requirements. This paper shows experimental studies using real data about six undergraduate courses in one the largest Brazilian public universities.