Sistema gerencial de avaliação automática do perfil do estudante
Educational system. Machine learning, Web platform.
The education system in Brazil, according to the organization for Economic Cooperation and Development (OECD), presents a stagnation that lasted for ten years, and, when evaluated in the 2018 edition of the International Student Assessment Program (Pisa), the country reached the areas of mathematics, science and literature respectively 70°, 66°, and 57°. This scenario maintaining due to the educational model adopted by the country that does not follow the advances in the area and the devaluation of professionals working in education, according to the OECD (2018), Brazilian teachers are the ones who receive the worst salaries among the 48 countries evaluated. To seek solutions to alleviate this scenario. The present work proposes to develop a system based on machine learning that will analyze the student’s profile to detect the main points of learning difficulty and thus be able to suggest adaptations in the students’ learning strategies. Also, carrying out a continuous performance analysis to find the most significant challenges of Brazilian students and suggest ways to solve them, thus generating a performance improvement. For this, the project will be tested first for programming logic at the School of Science and Technology of the Federal University of Rio Grande do Norte, as this is an environment controlled through a web platform that will extract data from each student and the class in general. In the future, These data are classified through a system based on supervised learning.