Machine Learning e a influencia das características infraestruturais e pedagógicas no desempenho escolar para o programa Milênio do MPBA

Abstract

Access to quality education is of paramount importance importance for the population, and several aspects can be influence students’ academic performance. Through the census school and it is possible to know the resources made available by teaching units. In the final stage of basic education, through of an assessment system, such as ENEM, it is possible, to In addition to other objectives, measuring the quality of teaching in schools based on the performance of their respective students. Within of this scenario, know what the infrastructural and pedagogical strategies most influence school performance is presented as an important tool to act more assertiveness in the points that can improve the quality of teaching. Therefore, this work aims to select the most relevant infrastructural and pedagogical characteristics for student performance in public teaching units and private companies in the country. For this, microdata were used of the school census, as well as ENEM micro data for school, with a time frame from 2009 to 2015. To carry out the feature selection, two groups of attributes were created related to infrastructure and pedagogy, subsequently, were selection methods based on filters, wrapper and embedded. The schools were classified into concepts ranging from ˜ A to D. Of the 389 columns present in the dataset, we selected 44 and their respective degrees of influence. The machine model learning resulting from the selection of attributes achieved 98.9% of the model performance without attribute selection.