Variable selection using random forests

被引：75

作者：

Sandri, Marco ^{[1
]}

Zuccolotto, Paola ^{[1
]}

机构：

[1] Univ Brescia, Dipartimento Metodi Quantitat, cda S Chiara 50, I-25122 Brescia, Italy

来源：

DATA ANALYSIS, CLASSIFICATION AND THE FORWARD SEARCH | 2006年

关键词：

D O I：

10.1007/3-540-35978-8_30

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One of the main topic in the development of predictive models is the identification of variables which axe predictors of a given outcome. Automated model selection methods, such as backward or forward stepwise regression, are classical solutions to this problem, but are generally based on strong assumptions about the functional form of the model or the distribution of residuals. In this paper an alternative selection method, based on the technique of Random Forests, is proposed in the context of classification, with an application to a real dataset.

引用

页码：263 / +

页数：2

共 14 条

[1] Bootstrap methods for developing predictive models [J].