C4.5 [22] is a decision tree algorithm. The usual splitting criterion to select an attribute is the gain ratio [20] based
on the information concept defined by Shannon [27]. Each tree level is generated by dividing the data at a given node
into a number of subsets, which are represented by branches. For each division, the gain ratio is used to select the
best attribute, whose values are used to divide the data into subsets. Each subset contains data that take on one of the
values of the selected attribute. It can work with both discrete and continuous data.