Cost-sensitive pruning of decision trees

  • Ulrich Knoll
  • Gholamreza Nakhaeizadeh
  • Birgit Tausend
Extended Abstracts
Part of the Lecture Notes in Computer Science book series (LNCS, volume 784)


The pruning of decision trees often relies on the classification accuracy of the decision tree. In this paper, we show how the misclassification costs, a related criterion applied if errors vary in their costs, can be integrated in several well-known pruning techniques.


  1. [BFOS84]
    L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone. Classification and Regression Trees. The Wadsworth and Brooks, Belmond, 1984.Google Scholar
  2. [BK87]
    I. Bratko, and I. Kononenko. Learning diagnostic rules from incomplete and noisy data. London Buisness School: Unicom Seminars Ltd, 1987.Google Scholar
  3. [Bos90]
    R. Boswell. Manual for NEWID, Version 4.1. Turing Institute, Glasgow,1990.Google Scholar
  4. [CB91]
    B. Cestnik, and I. Bratko. On Estimating Probabilities in Tree Pruning. In Machine Learning — EWSL-91 Learning. Springer, 1991.Google Scholar
  5. [Kno93]
    U. Knoll. Kostenoptimiertes Prunen in Entscheidungsbäumen. Diplomarbeit Nr. 924, Fakultät Informatik, Universität Stuttgart, 1993.Google Scholar
  6. [Min87]
    J. Mingers. Expert systems — rule induction with statistical data. Journal of the Operational Research Society, 38, 1987.Google Scholar
  7. [Min89]
    J. Mingers. An empirical comparison of pruning methods for decision tree induction. Machine Learning, 4, 1989.Google Scholar
  8. [Qui86]
    J.R. Quinlan. Induction of Decision Trees. Machine Learning, 1, 1986.Google Scholar
  9. [Qui87]
    J.R. Quinlan Simplifying decision trees. Int. J. Man-Machine Stud., 27, 1987.Google Scholar
  10. [Qui92]
    J.R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann,1992.Google Scholar
  11. [STA93]
    StatLog: Comparative Testing of Statistical and Logical Learning. Deliverable 4.1, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Ulrich Knoll
    • 1
  • Gholamreza Nakhaeizadeh
    • 1
  • Birgit Tausend
    • 2
  1. 1.Research and Technology, F3WDaimler-Benz AGUlmGermany
  2. 2.Fakultät InformatikUniversität StuttgartStuttgartGermany

Personalised recommendations