Table 1.

Abbreviations, acronyms, notations, and symbols employed in the present document.

Abbreviations/Acronyms		Notations/Symbols
ANN	artificial neural networks	∼	distributed as
CLU	clustering	k	number of nearest neighbors
CP	community poverty index	n	sample size
DT	decision trees	$l={\beta }_0+{\beta }_{1}x$	log-odd
EDM	educational data mining	$o=b^{{\beta }_0+{\beta }_{1}x}$	odd
EM	ensemble models	${\beta }_0,{\beta }_1$	regression coefficients
FN	false negative	X	independent variable or feature
FP	false positive	Y	dependent variable or response
HE	higher education	$p=P(Y=1)$	probability function of LR
IG	information gain	$=\frac{exp({\beta }_0+{\beta }_{1}x)}{exp({\beta }_0+{\beta }_{1}x)+1}$
KNN	k-nearest neighbors	$=\frac{1}{1+exp(-{\beta }_0-{\beta }_{1}x)}$
LR	logistic regression	$P(Y=c\mid \mathit{X}=\mathit{x})$	probability Y given $\mathit{X}$
ML	machine learning	$\frac{P(Y=c)P(\mathit{X}=\mathit{x}\mid Y=c)}{P(\mathit{X}=\mathit{x})}$	Bayes conditional probability
NB	naive Bayes	$\mathit{X}=(X_1,\dots ,X_p)$	vector of independent variables
NEM	secondary educational score	$(x_1,Y_1),\cdots ,(x_n,Y_n)$	instances
	(notas enseñanza media)	c	number of classes
PSU	university selection test	$\parallel x\parallel$	norm of a point x
	(prueba selección universitaria)	s	number of folds in cross-validation
RAM	random access memory	$\mathit{w}$	normal vector to the hyperplane
RF	random forest	TP/(TP + FP)	precision
SVM	support vector machines	$\kappa =(p_a-p_e)/(1-p_e)$	$\kappa$-statistic
TF	true negative	$p_a$	% of agreement classifier/ground truth
TP	true positive	$p_e$	agreement chance
UCM	Catholic University of Maule	$Q=\frac{12n}{c(c+1)}{\displaystyle \sum _{j=1}^c}{\left({\overline{r}}_{·j}-\frac{c+1}{2}\right)}^2$	Friedman statistic
	(Universidad Católica del Maule)	${\left\{x_{ij}\right\}}_{n\times c}$	$n\times c$ data matrix
SMOTE	synthetic minority	${\left\{r_{ij}\right\}}_{n\times c}$	$n\times c$ rank matrix
	over-sampling technique	${\overline{r}}_{·j}=\frac{1}{n}{\displaystyle \sum _{i=1}^n}{r}_{ij}$	rank average of column j
KDD	knowledge discovery	$P\left({\chi }_c^2\ge Q\right)$	p-value
	in databases	${\chi }_c^2$	chi-squared distribution
			with c degrees of freedom