ABSTRACT
The mining analogy is suggestive of finding a nugget or gem rather than pulling out rocks, rendering them to dust and reforming the dust into something valuable. The mining analogy is useful because it implies that some form of engineering will be needed to provide the tools for extracting the nuggets. Most data mining software acknowledges that data can come from a variety of sources, and it will provide ways of importing data from other formats such as binary, comma-separated values, universal resource locators, and databases. There are a number of criteria that have to be met for a data mining method to be considered practical. Minimally, an algorithm must have the ability to deal with numeric attributes, missing values, noise, and very large datasets. One of the most recent developments in data mining that is receiving much attention are algorithms for learning linear classifiers called support vector machines. The areas cover medicine, commerce, manufacturing, bioinformatics, and so on.
