Databases Reference
In-Depth Information
4
Prediction Algorithms for
Data Mining
In support of the data mining process, VisMiner implements algorithms for
prediction modeling. It supports modelers both for classification (predicting
nominal or class values) and regression (predicting continuous numeric
values). In this chapter we introduce the basic algorithms implemented by
VisMiner. These include decision trees, support vector machines, and
artificial neural networks for classification and artificial neural networks
for regression.
For the most part, the algorithms of VisMiner are a black box. One does not
need to know precisely how the algorithms work in order to deploy them in data
mining exercises. Consequently, this chapter may be skipped. However, knowl-
edge of the algorithms can help in the following ways:
Algorithm selection - each algorithm has its strengths and weaknesses. An
understanding of the internal workings of an algorithm leads to a better
appreciation of its strengths and weaknesses. Consequently it results in
better decision making when it comes to algorithm selection as dictated by
the dataset characteristics and data mining objective.
Results evaluation - knowing how the algorithm arrived at its results helps in
assessment of the applicability and confidence in the results. For example,
with respect to a decision tree, how does a root level split variable compare
in importance to a leaf level split?
