Abstract
Mining association rules is a well known framework for extracting useful knowledge from databases. They represent a very particular kind of relation, that of co-occurrence between two sets of items. Modifying the usual definition of such rules we may find different kinds of information in the data. Exception rules are examples of rules dealing with unusual knowledge that might be of interest for the user and there exists some approaches for extracting them which employ a set of special association rules.
The goal of this paper is manyfold. First, we provide a deep analysis of the presented previous approaches. We study their advantages, drawbacks and their semantical aspects. Second, we present a new approach using the certainty factor for measuring the strength of exception rules. We also offer a unified formulation for exception rules through the GUHA formal model first presented in the middle sixties by Hájek et al. Third, we define the so called double rules as a new type of rules which in conjunction with exception rules will describe in more detail the relationship between two sets of items. Fourth, we provide an algorithm based on the previous formulation for mining exception and double rules with reasonably good performance and some interesting results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Agrawal, R., Manilla, H., Sukent, R., Toivonen, A., Verkamo, A.: Fast discovery of Association rules, pp. 307–328. AAA Press (1996)
Berzal, F., Cubero, J., Marín, N., Gámez, M.: Anomalous association rules. In: IEEE Int. Conf. on Data Mining (2004)
Berzal, F., Delgado, M., Sánchez, D., Vila, M.: Measuring accuracy and interest of association rules: A new framework. Intelligent Data Analysis 6(3), 221–235 (2002)
Brachman, R., Levesque, H.: Knowledge Representation and Reasoning. Elsevier, Morgan Kaufmann publishers (2004)
Brewka, G.: Nonmonotonic Reasoning: Logical Foundations of Commonsense. University Press, Cambridge (1991)
Delgado, M., Marín, N., Sánchez, D., Vila, M.: Fuzzy association rules: General model and applications. IEEE Transactions on Fuzzy Systems 11(2), 214–225 (2003)
Delgado, M., Ruiz, M., Sánchez, D.: A logic approach for exceptions and anomalies in association rules. Mathware & Soft Computing 15(3), 285–295 (2008)
Delgado, M., Ruiz, M., Sánchez, D.: Studying interest measures for association rules through a logical model. Int. Journal of Uncertainty, Fuzziness and Knowledge-Based Systems (2007) (submitted)
Duval, B., Salleb, A., Vrain, C.: On the discovery of exception rules: A survey. Studies in Computational Intelligence 43, 77–98 (2007)
Hájek, P., Havel, I., Chytil, M.: The guha method of automatic hypotheses determination. Computing 1, 293–308 (1966)
Hájek, P., Havránek, T.: Mechanising Hypothesis Formation-Mathematical Foundations for a General Theory. Springer, Heidelberg (1978)
Havránek, T.: Statistical quantifiers in observational calculi: An application in guha-methods. Theory and Decision 6, 213–230 (1974)
Holeňa, M.: Fuzzy hypotheses for guha implications. Fuzzy Sets and Systems 98, 101–125 (1998)
Hussain, F., Liu, H., Suzuki, E., Lu, H.: Exception rule mining with a relative interestingness measure. In: Terano, T., Chen, A.L.P. (eds.) PAKDD 2000. LNCS, vol. 1805, pp. 86–97. Springer, Heidelberg (2000)
Louie, E., Lin, T.: Finding association rules using fast bit computation: Machine-oriented modeling. In: Ohsuga, S., Raś, Z.W. (eds.) ISMIS 2000. LNCS (LNAI), vol. 1932, pp. 486–494. Springer, Heidelberg (2000)
Ohshima, M., Zhong, N., Yao, Y., Liu, C.: Relational peculiarity-oriented mining. Data Mining and Knowledge Discovery 15(2), 249–273 (2007)
Rauch, J.: Logic of association rules. Applied Intelligence 22, 9–28 (2005)
Rauch, J., Šimunek, M.: Mining for 4ft association rules. In: Morishita, S., Arikawa, S. (eds.) DS 2000. LNCS (LNAI), vol. 1967, pp. 268–272. Springer, Heidelberg (2000)
Rauch, J., Šimunek, M.: An alternative approach to mining association rules. Studies in Computational Intelligence 6, 211–231 (2005)
Shortliffe, E., Buchanan, B.: A model of inexact reasoning in medicine. Mathematical Biosciences 23, 351–379 (1975)
Suzuki, E.: Discovering unexpected exceptions: A stochastic approach. In: Proceedings of the fourth international workshop on RSFD, pp. 225–232 (1996)
Suzuki, E.: Undirected discovery of interesting exception rules. Int. Jour. of Pattern Recognition and Artificial Intelligence 16(8), 1065–1086 (2002)
Suzuki, E., Shimura, M.: Exceptional knowledge discovery in databases based on information theory. In: Proc. of the 2nd Int. Conf. on Knowledge Discovery and Data Mining, pp. 275–278 (1996)
Suzuki, E., Zytkow, J.: Unified algorithm for undirected discovery of exception rules. Int. Jour. of Intelligent Systems 20, 673–691 (2005)
Zhong, N., Ohshima, M., Ohsuga, S.: Peculiarity oriented mining and its application for knowledge discovery in amino-acid data. In: Cheung, D., Williams, G.J., Li, Q. (eds.) PAKDD 2001. LNCS (LNAI), vol. 2035, pp. 260–269. Springer, Heidelberg (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Delgado, M., Ruiz, M.D., Sánchez, D. (2010). Mining Exception Rules. In: Bouchon-Meunier, B., Magdalena, L., Ojeda-Aciego, M., Verdegay, JL., Yager, R.R. (eds) Foundations of Reasoning under Uncertainty. Studies in Fuzziness and Soft Computing, vol 249. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10728-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-10728-3_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10726-9
Online ISBN: 978-3-642-10728-3
eBook Packages: EngineeringEngineering (R0)