Characterization of the students of a higher education institution through big data

Abstract

The article presents results of a research project whose main objective was to characterize students of a higher education institution through the use of big data techniques and tools. This with the purpose of providing the institution with a tool to support decision-making related to the student community. The project was developed in five phases: strategy definition; data capture and measurement; data analysis; results report; and, business transformation. As data analysis techniques, the Pearson correlation coefficient and the k-means grouping were used. As a result, an inventory and characterization of the data sources was obtained, as well as a model of analysis and information processing, when it is applied, generates a characterization of a student community.