A Performance Analysis of Classifiers on Imbalanced Data

Nathan Garcia, Rômulo Strzoda, Giancarlo Lucca, Eduardo Borges

2022

Abstract

In the machine learning field, there are many classification algorithms. Each algorithm performs better in certain scenarios, which are very difficult to define. There is also the concept of grouping multiple classifiers, known as ensembles, which aim to increase the model generalization capacity. Comparing multiple models is costly, as, for certain cases, training classifiers can take a long time. In the literature, many aspects of the data have already been studied to help in the task of classifier selection, such as measures of diversity among classifiers that form an ensemble, data complexity measures, among others. In this context, the main objective of this work is to analyze class imbalance and how this measure can be used to guide the selection of classifiers. We also compare the model’s performances when using class balancing techniques such as oversampling and undersampling.

Paper Citation

in Harvard Style

Garcia N., Strzoda R., Lucca G. and Borges E. (2022). A Performance Analysis of Classifiers on Imbalanced Data. In Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-758-569-2, pages 602-609. DOI: 10.5220/0011089100003179

in Bibtex Style

@conference{iceis22,
author={Nathan Garcia and Rômulo Strzoda and Giancarlo Lucca and Eduardo Borges},
title={A Performance Analysis of Classifiers on Imbalanced Data},
booktitle={Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2022},
pages={602-609},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011089100003179},
isbn={978-989-758-569-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - A Performance Analysis of Classifiers on Imbalanced Data
SN - 978-989-758-569-2
AU - Garcia N.
AU - Strzoda R.
AU - Lucca G.
AU - Borges E.
PY - 2022
SP - 602
EP - 609
DO - 10.5220/0011089100003179