On the other hand, advances in information technologies have made it possible
to collect, store and process massive, often highly complex datasets. All this
data hold valuable information such as trends and patterns, which can be used to
improve decision making and optimize chances of success [23]. Data mining (DM)
techniques [26] aim at extracting high-level knowledge from raw data. There
are several DM algorithms, each one with its own advantages. When modeling
continuous data, the linear/multiple regression (MR) is the classic approach.
Neural networks (NNs) have become increasingly used since the introduction
of the backpropagation algorithm [19]. More recently, support vector machines
(SVMs) have also been proposed [3]. Due to their higher flexibility and nonlinear
learning capabilities, both NNs and SVMs are gaining an attention within
the DM field, often attaining high predictive performances [13]. SVMs present
theoretical advantages over NNs, such as the absence of local minima in the
learning phase. When applying these methods, performance highly depends on
a correct variable and model selection, since simple models may fail in mapping
the underlying concept and too complex ones tend to overfit the data