Prediction of school dropout risk group using Neural Network

Dropping out of school is one of the most complex and crucial problems in education, causing social, economic, political, academic and financial losses. In order to contribute to solve the situation, this paper presents the potentials of an intelligent, robust and innovative system, developed for the prediction of risk groups of student dropout, using a Fuzzy-ARTMAP Neural Network, one of the techniques of artificial intelligence, with possibility of continued learning. This study was conducted under the Federal Institute of Education, Science and Technology of Mato Grosso, with students of the Colleges of Technology in Automation and Industrial Control, Control Works, Internet Systems, Computer Networks and Executive Secretary. The results showed that the proposed system is satisfactory, with global accuracy superior to 76% and significant degree of reliability, making possible the early identification, even in the first term of the course, the group of students likely to drop out.