NEW BAYESIAN SIMPLE CLASSIFIER FOR EDUCATIONAL DATA ANALYSIS

In this article, we propose the use of a new simple Bayesian classifier (SBND) that quickly learns a Markov boundary of the class variable and a red structure that relates the variables of the class and the boundary. This model is compared with other Bayesian classificators, to then make use of probabilistic graphical models in the field of education in order to determine the problem of student desertion in universities. Socio-economic data of students legally enrolled in the Faculty of Engineering Sciences of the Technical State University of Quevedo in Ecuador during the 2012-2013 period have been used. This database compares the results obtained with the Naive Bayes, TAN, BAN, SBND and combinations with different metrics such as K2, BIC, Akaike, BDEu. The RPDAG and C-RPDAG methods are also compared. The experimental work was carried out with the Weka tool, which is free and has open access.