Sistema gerencial de avaliação automática do perfil do estudante

Abstract

It is known that the educational system in Brazil, according to the Organization for Economic Cooperation and Development (OECD), presents a stagnation that lasts for 10 years and when evaluated in the 2018 edition of the Program for International Student Assessment (Pisa) the country achieved in the areas of mathematics, science and literature respectively 70th, 66th, and 57th. This scenario is maintained 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 those who receive the worst salaries among the 48 countries evaluated. In order to seek solutions to alleviate this scenario. The present work proposes to develop a system based on machine learning to carry out a continuous analysis of the student’s profile, suggestion of activities, and monitoring of academic performance. In addition, performing a student performance analysis in order to find metrics and markers to create an adaptive and standardized model in the future. For this, the project was first evaluated for the subject of 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 the data of each student and the class. in general. Furthermore, the standard of submission of student activities was also analyzed. These data will be classified through a system based on supervised learning. And finally, the planning and market analyses for the sale and traction of this product were carried out.