Ratio Rules: A New Paradigm for Fast, Quantifiable Data Mining
DocUID: 1998-004 Full Text:
PDF Author: Flip Korn, Alexandros Labrinidis, Yannis Kotidis, Christos Faloutsos
Abstract: Association Rule Mining algorithms operate on a data matrix (e.g., customers \Theta products) to derive association rules [2, 23]. We propose a new paradigm, namely, Ratio Rules, which are quantifiable in that we can measure the "goodness" of a set of discovered rules. We propose to use the "guessing error" as a measure of the "goodness", that is, the rootmean -square error of the reconstructed values of the cells of the given matrix, when we pretend that they are unknown.
Published In: In Proc. 24th Int. Conf. Very Large Data Bases
ISBN: 1-55860-566-5
Pages: pp. 582-593
Place Published: New York City
Year Published: 1998
Project: Others Subject Area: Others
Publication Type: Conference Paper
Sponsor: Others