Data mining model to predict academic performance at the Universidad Nacional de Colombia
Abstract. The present research proposes an approach to Educational Data Mining at the Universidad Nacional de Colombia through the definition of models that integrate clustering and classification techniques to analyze academic data, corresponding to the students who joined the University to the pro...
- Autores:
-
López Guarín, Camilo Ernesto
- Tipo de recurso:
- Fecha de publicación:
- 2013
- Institución:
- Universidad Nacional de Colombia
- Repositorio:
- Universidad Nacional de Colombia
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.unal.edu.co:unal/51303
- Acceso en línea:
- https://repositorio.unal.edu.co/handle/unal/51303
http://bdigital.unal.edu.co/45384/
- Palabra clave:
- 0 Generalidades / Computer science, information and general works
37 Educación / Education
62 Ingeniería y operaciones afines / Engineering
Data mining
Dropout
Education
Minería de Datos
Deserción
Educación
- Rights
- openAccess
- License
- Atribución-NoComercial 4.0 Internacional
Summary: | Abstract. The present research proposes an approach to Educational Data Mining at the Universidad Nacional de Colombia through the definition of models that integrate clustering and classification techniques to analyze academic data, corresponding to the students who joined the University to the programs of Agricultural and Computer and Systems Engineering between 2007-03 and 2012-01. These techniques are intended to acquire a better understanding of the attrition during the first enrollments and to assess the quality of the data for the classification task, which can be understood as the prediction of the loss of academic status due to low academic performance. Different models were built to predict the loss of academic status in different scenarios such as: in the first four enrollments regardless when; at a specific academic period using only the admission process data and then, using academic records. Experimental results show that the prediction of the loss of academic status is improved when adding academic data. |
---|