Regression trees represent one of the most popular tools in predictive data mining applications. However, their performances severely degrade in the presence of highly-skewed and/or long-tailed error distributions, and especially for grossly mis-measured values of the dependent variable. In this paper, these issues are discussed from both a theoretical and a practical point of view, and some recent proposals to overcome these difficulties are presented.
G. Galimberti, M. Pillati, G. Soffritti (2009). Some issues on robustness of regression trees. PADOVA : CLEUP.
Some issues on robustness of regression trees
GALIMBERTI, GIULIANO;PILLATI, MARILENA;SOFFRITTI, GABRIELE
2009
Abstract
Regression trees represent one of the most popular tools in predictive data mining applications. However, their performances severely degrade in the presence of highly-skewed and/or long-tailed error distributions, and especially for grossly mis-measured values of the dependent variable. In this paper, these issues are discussed from both a theoretical and a practical point of view, and some recent proposals to overcome these difficulties are presented.File in questo prodotto:
Eventuali allegati, non sono esposti
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
