Engineering Students´ Academic Performance Prediction using ICFES Test Scores and Demo-graphic Data

Sandra Merchán Rubiano, Adán Beltrán Gómez, Jorge Duarte García

Resumen


Introduction: This paper is part of a research project that aims to construct a predictive model for students’ academic performance, as result of an iterative process of experimentation and evaluation of the pertinence of some data mining techniques. Methodology: This paper was written in 2016 in the Universidad El Bosque, Bogotá, Colombia, and presents a comparative analysis of the performance and relevance of the J48 and Random Forest algorithms, in order to identify the most influential demographic and icfes score variables, as well as the classification rules, to predict the first year academic performance of the Engineering Faculty students, in Universidad El Bosque, Bogotá, Colombia. Results: The analysis process was carried out on 7,644 students’ records, and it was developed in two phases. Firstly, the data needed to feed the mining process was extracted and prepared. Secondly, the data mining process itself was implemented through preprocessing data and executing the classification algorithms available in Weka. Some significant variables and rules to predict academic performance are found, according to the studied population characteristics. Conclusions: The academic risk seen as the cause of the desertion phenomenon must be studied as a phenomenon itself. Establishing its causes facilitates the creation of preventive strategies for the accompaniment of students through their process, aimed to mitigate the risk of both phenomena.


Palabras clave


academic performance prediction; academic risk prevention; data mining; J48; Random Forest;

Texto completo:

PDF (English)

Referencias


C. Guzman R., D. Duran M., J. Franco G., E. Castaño V., S. Gallon G., K. Gomez P. and J. Vas-quez V. Deserción Estudiantil En La Educación Superior Colombiana. Metodología De Seguimiento, Diagnóstico Y Elementos Para Su Prevención 2009.

Pruebas Saber. Available: http://www.mineducacion.gov.co/1759/w3-article-244735.html.

Centro de Estudios sobre Desarrollo Económico, CEDE, "Determinantes de la deserción," Febrero 14, 2014.

N. Suárez-Montes and L. B. Díaz-Subieta. “Estrés académico, deserción y estrategias de retención de estudiantes en la educación superior”. Revista De Salud Pública, 17(2), pp. 300-313. 2015. . DOI: 10.15446/rsap.v17n2.52891.

M. Astudillo, "FACTORES DE RIESGO ASOCIADOS A LA DESERCIÓN ESTUDIANTIL EN LA UNIVERSIDAD ICESI," Mayo, 2013.

De la Rosa, Juan Carlos, R. Linero, I. Meriño and O. Rodríguez. "Acompañamiento de estudiantes en alto riesgo académico" in Encuentro Internacional De Educación En Ingeniería ACOFI 2014.  Septiembre, 2014, pp. 118-119.

F. Barrero, C. Barrero, H. Borja and M. Montaño. Factores de riesgo asociados a la deserción estu-diantil universitaria en programas de pregrado de la Universidad de San Buenaventura, Bogotá (2009-2013) 1. Academia Y Virtualidad 2(8), pp. 60-72. 2015. Availa-ble: http://revistas.unimilitar.edu.co/index.php/ravi/article/view/1423. DOI: //dx.doi.org/10.18359/ravi.1423.

E. P. Ibarra Garcia and P. Medina Mora, "Model prediction of academic performance for first year students" in 2011, pp. 169-174.

S. Taruna and M. Pandey. An empirical analysis of classification techniques for predicting academic performance. 2014, Available: http://ieeexplore.ieee.org/document/6779379. DOI: 10.1109/IAdCC.2014.6779379.

G. Gray, C. McGuinness and P. Owende. An application of classification models to predict learner progression in tertiary education. 2014. Available: http://ieeexplore.ieee.org/document/6779384. DOI: 10.1109/IAdCC.2014.6779384.

Nguyen Thai Nghe, P. Janecek and P. Haddawy. A comparative analysis of techniques for predict-ing academic performance. 2007. Available: http://ieeexplore.ieee.org/document/4417993. DOI: 10.1109/FIE.2007.4417993.

S. M. Merchan Rubiano and J. A. Duarte Garcia. Formulation of a predictive model for academic performance based on students' academic and demographic data. Presented at Frontiers in Education (Conference). 2015, Available: http://ieeexplore.ieee.org/document/7344047. DOI: 10.1109/FIE.2015.7344047.

S. M. Merchan Rubiano and J. A. Duarte Garcia. “Analysis of data mining techniques for construct-ing a predictive model for academic performance”. T-La 14(6), pp. 2783-2788. 2016. Availa-ble: http://ieeexplore.ieee.org/document/7555255. DOI: 10.1109/TLA.2016.7555255.

S. M. Merchan Rubiano and J. A. Duarte Garcia, "Analysis of data mining techniques for construct-ing a predictive model for academic performance," in UNESCO-UNIR ICT & Education Latam Congress 2016  pp. 39-48.

(The University of Waikato). Weka 3: Data Mining Software in Java. Availa-ble: http://www.cs.waikato.ac.nz/ml/weka


comments powered by Disqus

DOI: https://doi.org/10.16925/in.v13i21.1729

Métricas de artículo

Cargando métricas ...

Metrics powered by PLOS ALM


Contacto

Línea gratuita nacional

01 8000 420101

Dirección

Facultad de Ingeniería
Avenida Caracas no. 37-15 
Bogotá, D.C.

Teléfono

(57) (1) 3323565

(57) 3004956353

Revista en OJS implementada por Biteca Ltda.