Advertisement

Probabilistic Approach to Association Rules in Incomplete Databases

  • Marzena Kryszkiewicz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1846)

Abstract

In the paper we list a set of properties that characterize a legitimate approach to data incompleteness. An example of a legitimate probabilistic approach, which is based on attribute distribution, is presented. We also review and compare three other approaches to incompleteness: the one that ignores missing values, the approach applying only certain information, and the approach based on valid databases. All the three approaches turn out to be invalid.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Agrawal, R., Imielinski, T., Swami, A.: Mining Associations Rules between Sets of Items in Large Databases. In: Proc. of the ACM SIGMOD Conference on Management of Data. Washington, D.C. (1993) 207–216Google Scholar
  2. 2.
    Kononenko, I., Bratko, I., Roskar, E.: Experiments in Automatic Learning of Medical Diagnostic Rules. Technical Report. Jozef Stefan Institute, Ljubljana, Yugoslavia (1984)Google Scholar
  3. 3.
    Kryszkiewicz, M.: Association Rules in Incomplete Databases: In: Lecture Notes in Artificial Intelligence 1574, Methodologies for Knowledge Discovery and Data Mining, Proc. of Third Pacific-Asia Conference, PAKDD’ 99, Beijing, China, 26–28 1999, Springer (1999) 84–93Google Scholar
  4. 4.
    Quinlan J.R.: Induction of Decision Trees. In: Shavlik J. W., Dietterich T.G. (eds.): Readings in Machine Learning. Morgan Kaufmann Publishers (1990) 57–69Google Scholar
  5. 5.
    Ragel A., Cremilleux B.: Treatment of Missing Values for Association Rules. In: Proc. of Second Pacific Asia Conference, PAKDD’98. Melbourne, Australia. LNAI 1394. Research and Development in Knowledge Discovery and Data Mining. Springer (1998) 258–270Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Marzena Kryszkiewicz
    • 1
  1. 1.Institute of Computer ScienceWarsaw University of TechnologyWarsawPoland

Personalised recommendations