Component-Based User Guidance in Knowledge Discovery and Data Mining

Share
Editor
Engels, R.
Pub. date
January 1999
Pages
234
Binding
softcover
Volume
211 of Dissertations in Artificial Intelligence
ISBN print
978-1-58603-114-5
Subject
Artificial Intelligence, Computer & Communication Sciences, Computer Science

Knowledge Discovery and Data Mining (KDD) is a relatively young field of research with a rapidly increasing number of techniques supporting it. This fact, combined with the ability of state-of-the-art technology to capture and store large quantities of data, led to the research described in this thesis.


A general methodology for the definition, support, reuse and documentation of KDD processes is described. Topics like the description of the context in which KDD has to be performed, selection and instantiation of appropriate techniques as well as the context specific reuse of KDD processes are addressed. As a result of the research conducted, a prototypical implementation of the "User Guidance Module" is made in order to demonstrate the feasibility of the approach.


Bringing together the fields of Knowledge Discovery and Data Mining, Knowledge Engineering and Statistics, this thesis proposes and refines a methodology for support of definition and elaboration of solutions for KDD problems.