Data Mining and Knowledge Discovery in Databases

Data Mining And The Knowledge Discovery In Databases Process

“The KDD process, as presented in (Fayyad, Piatetski-Shapiro, & Smyth, 1996), is the process of using DM methods to extract what is considered knowledge according to the specification of measures and thresholds, using a database along with any required preprocessing, sub sampling, and transformation of the database. There are five stages considered, namely, selection, preprocessing, transformation, data mining, and interpretation/evaluation as presented in Figure 1:

• •

  Selection: This stage consists on creating a target data set, or on focusing in a subset of variables or data samples, on which discovery is to be performed;

• •

  Preprocessing: This stage consists on the target data cleaning and preprocessing in order to obtain consistent data;

• •

  Transformation: This stage consists on the transformation of the data using dimensionality reduction or transformation methods;

• •

  Data Mining: This stage consists on the searching for patterns of interest in a particular representational form, depending on the DM objective (usually, prediction);

• •

  Interpretation/Evaluation: This stage consists on the interpretation and evaluation of the mined patterns.” (Azevedo & Santos, 2008, p. 183)

Figure 1.

The KDD process