Minería de datos a través de CRM para identificar el tipo de estudiantes que ingresan a la Escuela Miguel Ángel Suárez de la ciudad de Loja

Abstract

Abstract: This paper presents an evaluation of data mining algorithms applied to the educational field, focusing on the identification and profiling of students entering secondary level educational institutions. The research uses well-established data mining methodologies and focuses on the implementation of classification and clustering algorithms, such as Naive Bayes and K-Means. Through the analysis of historical data and the generation of synthetic data, it was possible to segment students according to key socio-demographic and academic characteristics, allowing not only a better understanding of the entrance profiles, but also the prediction of future applicants. The results obtained validate the relevance of these techniques for creating effective recruitment strategies and making informed decisions.