A STUDY OF DECISION TREE ALGORITHMS FOR CONTINUOUS ATTRIBUTES

Authors

  • Ieva Boļakova Daugavpils Pedagogical University (LV)

DOI:

https://doi.org/10.17770/etr2001vol1.1922

Keywords:

decision trees, CART, C4.5

Abstract

Nowadays a lot of different algorithms for decision trees construction exist. With the help o f these algorithms one can make classification o f both discrete and continuous data. The aim o f this paper is to explore decision tree algorithms for continuous attributes. There are investigated CART (Breiman et al, 1984) and C4.5 (Quinlan, 1992) in this paper. The comparison of these methods was done in the process of exploration. As a result of the usage o f both algorithms, the conclusions about CART and C4.5 utilization advantages were drawn.

Downloads

Download data is not yet available.

References

Breiman L., Freidman J., etc. Classification and Regression Trees. - Wadsworth International, Monterey, 1984

Quinlan J.R. C4.5: Programs for Machine Learning - The Morgan Kaufmann Series in Machine Learning, Pat Langley, Series Editor, 1992

Quinlan J.R. Improved Use of Continues Attributes in C4.5. - Journal of Artificai Intelligence Research 4,3/96, 77-90, http://www.cs.washington.edu/research/jair/abstracts/quinlan96a.html

Downloads

Published

2001-06-20

How to Cite

[1]
I. Boļakova, “A STUDY OF DECISION TREE ALGORITHMS FOR CONTINUOUS ATTRIBUTES”, ETR, vol. 1, pp. 248–250, Jun. 2001, doi: 10.17770/etr2001vol1.1922.