Unknown

Dataset Information

0

A Random Forests Quantile Classifier for Class Imbalanced Data.


ABSTRACT: Extending previous work on quantile classifiers (q-classifiers) we propose the q*-classifier for the class imbalance problem. The classifier assigns a sample to the minority class if the minority class conditional probability exceeds 0 < q* < 1, where q* equals the unconditional probability of observing a minority class sample. The motivation for q*-classification stems from a density-based approach and leads to the useful property that the q*-classifier maximizes the sum of the true positive and true negative rates. Moreover, because the procedure can be equivalently expressed as a cost-weighted Bayes classifier, it also minimizes weighted risk. Because of this dual optimization, the q*-classifier can achieve near zero risk in imbalance problems, while simultaneously optimizing true positive and true negative rates. We use random forests to apply q*-classification. This new method which we call RFQ is shown to outperform or is competitive with existing techniques with respect to tt-mean performance and variable selection. Extensions to the multiclass imbalanced setting are also considered.

SUBMITTER: O'Brien R 

PROVIDER: S-EPMC6370055 | biostudies-literature | 2019 Jun

REPOSITORIES: biostudies-literature

altmetric image

Publications

A Random Forests Quantile Classifier for Class Imbalanced Data.

O'Brien Robert R   Ishwaran Hemant H  

Pattern recognition 20190129


Extending previous work on quantile classifiers (<i>q</i>-classifiers) we propose the <i>q</i>*-classifier for the class imbalance problem. The classifier assigns a sample to the minority class if the minority class conditional probability exceeds 0 <i>< q</i>* <i><</i> 1, where <i>q</i>* equals the unconditional probability of observing a minority class sample. The motivation for <i>q</i>*-classification stems from a density-based approach and leads to the useful property that the <i>q</i>*-cla  ...[more]

Similar Datasets

| S-EPMC7303690 | biostudies-literature
| S-EPMC3098087 | biostudies-literature
| S-EPMC5456046 | biostudies-literature
| S-EPMC7206335 | biostudies-literature
| S-EPMC3648438 | biostudies-other
| S-EPMC7303714 | biostudies-literature
| S-EPMC7242357 | biostudies-literature
| S-EPMC3163175 | biostudies-literature
| S-EPMC2335306 | biostudies-literature
| S-EPMC6598279 | biostudies-literature