An data egineering architecture for analyzing the Zone of Proximal Development of public school students in Brazil

In the didactic approach, Lev Bygotsky developed what he would classify as ZDP: Zone of Proximal Development, whose main objective wold be to measure student learning. This demonstrate how data engineering can facilitate the classification of ZDP for use in brazilian public schools.
Therefore, the use of mining tools, like Scrapy or Beautiful Soup, was essential for collecting students' pedagogical data from the platforms of the Alagoas state government. With the data in hand, it was up to the teacher to define the student's learning zones, based on teaching goals under the subject syllabus: assessments, activities and playful moments for the student's understanding of the subject studied.
Thus, with the influence of the teacher and the information collected from the student, it was possible to create a machine learning model, specifically a supervised classification model, which evaluates the student's performance and returns the current learning level, taking into account their pedagogical needs to be delivered to the teacher.
With the application, public school teachers were able to diagnose students according to their pedagogical needs, directly influencing student performance when these needs were met. This data architecture was able to directly meet a need that is still evident in public schools in the state of Alagoas in Brazil.