
170 ◾ Corlane Barclay
4. Data reduction and projection consists of nding useful attributes by applying
dimension reduction and transformation methods, and nding invariant rep-
resentation of the data.
5. Choosing the data mining task involves aligning the goals dened in step 1 with
a particular data mining method, such as classication, regression, and clustering.
6. Choosing the data mining algorithm consists of selection of methods to
search for patterns in the data and decides which models and parameters of
the methods used may be appropriate.
7. Data mining step generates the patterns in a particular representational form.
8. ...