Minería de datos aplicada a la clasificación del rendimiento académico

The present work of degree was developed with the objective of applying the main data mining algorithms used in education to make inferences in the classification of the academic performance of the students of the computing career of the ESPAM MFL. The tool used for the analysis process was the WEKA (Waikato Environment for Knowledge Analysis) software. In addition, the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology was used, which is structured in phases of development. Initially, the information was sought from existing research which allowed us to perform an approach to the algorithms and variables to apply, also the adaptation of the data was carried out according to the selected tool, once the data were prepared, the most appropriate techniques were applied and the pertinent tests were carried out to determine the usefulness of the models obtained from the variables that were evaluated. It was established that the main algorithms of the classification technique are J48, Naïve Bayes, Random Forest and OneR since these are the most used in educational data mining due to their accuracy in the classification of data, with the models determined that the variables that most affect the classification of academic performance of students are: academic state, semester and sub-total, these algorithms were applied in order to obtain a model that generates knowledge that supports decision-making in the education process higher.

• Autor principal: Cevallos Molina, Sulay Katerine (author)
• Altres autors: Trujillo Utreras, Viviana Katherine (author)
• Format: bachelorThesis
• Idioma: spa
• Publicat: 2018
• Matèries: Minería de datos; Rendimiento Académico; Árbol de Decisión; Naïve Bayes
• Accés en línia: http://repositorio.espam.edu.ec/handle/42000/862