Advertisement

Induction of Modular Classification Rules: Using Jmax-pruning

  • Frederic Stahl
  • Max Bramer
Conference paper

Abstract

The Prism family of algorithms induces modular classification rules which, in contrast to decision tree induction algorithms, do not necessarily fit together into a decision tree structure. Classifiers induced by Prism algorithms achieve a comparable accuracy compared with decision trees and in some cases even outperform decision trees. Both kinds of algorithms tend to overfit on large and noisy datasets and this has led to the development of pruning methods. Pruning methods use various metrics to truncate decision trees or to eliminate whole rules or single rule terms from a Prism rule set. For decision trees many pre-pruning and postpruning methods exist, however for Prism algorithms only one pre-pruning method has been developed, J-pruning. Recent work with Prism algorithms examined J-pruning in the context of very large datasets and found that the current method does not use its full potential. This paper revisits the J-pruning method for the Prism family of algorithms and develops a new pruning method Jmax-pruning, discusses it in theoretical terms and evaluates it empirically.

Keywords

Decision Tree Training Instance Target Class Rule Induction Pruning Method 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    C L Blake and C J Merz. UCI repository of machine learning databases. Technical report, University of California, Irvine, Department of Information and Computer Sciences, 1998.Google Scholar
  2. 2.
    M A Bramer. Automatic induction of classification rules from examples using N-Prism. In Research and Development in Intelligent Systems XVI, pages 99–121, Cambridge, 2000. Springer-Verlag.Google Scholar
  3. 3.
    M A Bramer. An information-theoretic approach to the pre-pruning of classification rules. In B Neumann M Musen and R Studer, editors, Intelligent Information Processing, pages 201–212. Kluwer, 2002.Google Scholar
  4. 4.
    M A Bramer. Inducer: a public domain workbench for data mining. International Journal of Systems Science, 36(14):909–919, 2005.MATHCrossRefGoogle Scholar
  5. 5.
    J. Cendrowska. PRISM: an algorithm for inducing modular rules. International Journal of Man-Machine Studies, 27(4):349–370, 1987.MATHCrossRefGoogle Scholar
  6. 6.
    F Esposito, D Malerba, and G Semeraro. A comparative analysis of methods for pruning decision trees. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(5):476–491, 1997.CrossRefGoogle Scholar
  7. 7.
    E B Hunt, P J Stone, and J Marin. Experiments in induction. Academic Press, New York, 1966.Google Scholar
  8. 8.
    R Kerber. Chimerge: Discretization of numeric attributes. In AAAI, pages 123–128, 1992. Frederic Stahl and Max BramerGoogle Scholar
  9. 9.
    R S Michalski. On the Quasi-Minimal solution of the general covering problem. In Proceedings of the Fifth International Symposium on Information Processing, pages 125–128, Bled, Yugoslavia, 1969.Google Scholar
  10. 10.
    R J Quinlan. C4.5: programs for machine learning. Morgan Kaufmann, 1993.Google Scholar
  11. 11.
    P. Smyth and R M Goodman. An information theoretic approach to rule induction from databases. Transactions on Knowledge and Data Engineering, 4(4):301–316, 1992.CrossRefGoogle Scholar
  12. 12.
    F T Stahl. Parallel Rule Induction. PhD thesis, University of Portsmouth, 2009.Google Scholar
  13. 13.
    F T Stahl,MA Bramer, and MAdda. PMCRI: A parallel modular classification rule induction framework. In MLDM, pages 148–162. Springer, 2009.Google Scholar
  14. 14.
    I H Witten and F Eibe. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, 1999.Google Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  1. 1.University of Portsmouth, School of ComputingPortsmouthUK

Personalised recommendations