Abstract
In this paper, we propose a way to improve the rule-learning step in a Knowledge Discovery in Databases (KDD) process. Our purpose is to make possible the discovery of relevant rules in a large database.
To achieve this goal, we merge:
-
a quality index proposed by R. Gras: intensity of implication.
-
together with a specific algorithm written by Agrawal et al. The algorithm itself is efficient in a large database but delivers a prohibitively large set of knowledge.
Intensity of implication is a new measurement of the quality of association rules. Hence, we analyze it in detail and compare it with conditional probability index. We show that it is possible to significantly improve the relevance of association rules supplied by the algorithm proposed by Agrawal et al, by using the quality index: intensity of implication.
An improved algorithm has been implemented, and has been tested both at the experimental level and on a real-life database.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Matheus C.J., Chan P.K., Piatetsky-shapiro G: Systems for Knowledge Discovery in Databases, IEEE Trans. Knowl. Data Eng., vol. 5, no 6, (1993)
Frawley W.J., Piatetsky-Shapiro G., Matheus J.: Knowledge Discovery in Databases: an overview, in Knowledge Discovery in Databases, Cambridge, MA: AAAI/MIT (1991) pp. 1–27
Agrawal R., Imielinski T., and Swami A.: Mining Association Rules between Sets of Items in Large Databases. In Proceedings, ACM SIG-MOD Conference on Management of Data, 207–216, Washington, D.C. (1993)
Agrawal R., And Srikant R.: Fast Algorithms for Mining Association Rules. IBM Research Report RJ9839, IBM Almaden Research Center, San Jose, Calif. (1994)
Agrawal R., Mannila H., Srikant R., Toivonen H. et Inkeri Verkamo A.: Fast Discovery of Association Rules, Advances in Knowledge Discovery and Data Mining, AAAI Press, The MIT Press (1996)
Guillaume S., Guillet F., Philippé J.: Contribution of the integration of intensity of implication into the algorithm proposed by Agrawal, EMCSR’98, Vienna, vol. 2, pp. 805–810, April (1998)
Gras R.: Contribution à l’Étude Expérimentale et à l’Analyse de Certaines Acquisitions Cognitives et de Certains Objectifs Didactiques en Mathématiques, Thèse d’État, Université de Rennes 1 (1979)
Gras R., Larher A.: L’Implication Statistique, une Nouvelle Méthode d’Analyse de Données, Mathématiques, Informatique et Sciences Humaines no120 (1993)
Gras R., Ag. Almouloud S., Bailleuil M., Larher A., Polo M., Ratsimba-Rajohn H., Totohasina A.: L’Implication Statistique, Nouvelle Méthode Exploratoire de Données. Application à la Didactique, Travaux et Thèses, édition La Pensée Sauvage (1996)
Anderson T.W.: An Introduction to Multivariate Statistical Analysis, Series in Probability and Mathematical Statistics, John Wiley and Son (1984) reviewed edition
Fleury L., Masson Y., Gras R., Briand H., Philippe J.: A Statistical Measure of Rule Strength for Machine Learning, 2d World Conference on the Fundamentals of Artificial Intelligence, WOCFAI, Paris (1995)
Fleury L., Briand H., Philippe J., Djeraba C.: Rules Evaluations for Knowledge Discovery in Database, 6th International Conference and Workshop on Database and Expert Systems Applications, DEXA, London (1995)
Fleury L., Masson Y.: The Intensity of Implication, a Measurement for Machine Learning, The 8th Int. Conf. On Industrail and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AEI, Melbourne (1995)
Lehn R., Guillet F., Briand H.: Eliminating redundant knowledge in a association rulebased system: An algorithm, EMCSR’98, Vienna, vol. 2, pp. 793–798, April (1998)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guillaume, S., Guillet, F., Philippé, J. (1998). Improving the discovery of association rules with intensity of implication. In: Żytkow, J.M., Quafafou, M. (eds) Principles of Data Mining and Knowledge Discovery. PKDD 1998. Lecture Notes in Computer Science, vol 1510. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0094834
Download citation
DOI: https://doi.org/10.1007/BFb0094834
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65068-3
Online ISBN: 978-3-540-49687-8
eBook Packages: Springer Book Archive