@article{Kuncheva2019,
title = {Instance selection improves geometric mean accuracy: a study on imbalanced data classification},
author = {Ludmila I Kuncheva and Álvar Arnaiz-González and José Francisco Díez-Pastor and Iain A D Gunn},
url = {https://link.springer.com/article/10.1007/s13748-019-00172-4?wt_mc=Internal.Event.1.SEM.ArticleAuthorOnlineFirst&utm_source=ArticleAuthorContributingOnlineFirst&utm_medium=email&utm_content=AA_en_06082018&ArticleAuthorContributingOnlineFirst_20190209},
doi = {10.1007/s13748-019-00172-4},
issn = {2192-6352},
year = {2019},
date = {2019-06-01},
journal = {Progress in Artificial Intelligence},
volume = {8},
number = {2},
pages = {215-228},
abstract = {A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data.},
keywords = {Ensemble methods, geometric mean (GM), Imbalanced data, instance/prototype selection, nearest neighbour, Theoretical perspective},
pubstate = {published},
tppubtype = {article}
}

A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data.

@article{Kuncheva2018,
title = {Instance Selection Improves Geometric Mean Accuracy: A Study on Imbalanced Data Classification},
author = {Ludmila I Kuncheva and Álvar Arnaiz-González and José Francisco Díez-Pastor and Iain A D Gunn},
url = {https://arxiv.org/abs/1804.07155},
doi = {arXiv:1804.07155v1},
year = {2018},
date = {2018-04-19},
journal = {arXiv},
abstract = {A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data. },
keywords = {Ensemble methods, geometric mean (GM), Imbalanced data, instance/prototype selection, nearest neighbour},
pubstate = {published},
tppubtype = {article}
}

A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data.

We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.Ok