ImbTreeAUC-package: An R package for building classification trees using Area...

In KrzyGajow/ImbTreeAUC: Software to build Decision Trees for imbalanced data

Description

An R package for building binary and multiclass decision tree algorithms using Area Under the Receiver Operating Characteristic (ROC) Curve, to measure impurity of a node. The package provides non-standard measures to select an optimal split point for an attribute as well as the optimal attribute for splitting through the application of local, semi-global and global AUC measures. Additionally, ImbTreeAUC is able to handle imbalanced data which is a challenging issue in many practical applications. The package supports cost-sensitive learning by defining a misclassification cost matrix and weight sensitive learning. It accepts all types of attributes, including continuous, ordered and nominal.

Author(s)

Krzysztof Gajowniczek

Maintainer: [e-mail]

See Also

ImbTreeAUC, ImbTreeAUCInter, PredictTree, PrintTree, PrintTreeInter, ExtractRules

KrzyGajow/ImbTreeAUC documentation built on March 7, 2021, 1:24 a.m.