<abstract xmlns="http://www.w3.org/1999/xhtml"><bold>Research background:</bold> The successful learning of classifiers depends on the quality of data. Modeling is especially difficult when the data are unbalanced or contain many irrelevant variables. This is the case in many applications. The classification of rare events is the overarching goal, e.g. in bankruptcy prediction, churn analysis or fraud detection. The problem of irrelevant variables accompanies situations where the specification of the model is not known <italic>a priori</italic>, thus in typical conditions for data mining analysts.<bold>Purpose:</bold> The purpose of this paper is to compare the combinations of the most popular strategies of handling unbalanced data with feature selection methods that represent filters, wrappers and embedded methods.<bold>Research methodology:</bold> In the empirical study, we use real datasets with additionally introduced irrelevant variables. In this way, we are able to recognize which method correctly eliminates irrelevant variables.<bold>Results:</bold> Having carried out the experiment we conclude that over-sampling does not work in connection with feature selection. Some recommendations of the most promising methods also are given.<bold>Novelty:</bold> There are many solutions proposed in the literature concerning unbalanced data as well as feature selection. The innovative field of our interests is to examine their interactions.</abstract>

Research background: The successful learning of classifiers depends on the quality of data. Modeling is especially difficult when the data are unbalanced or contain many irrelevant variables. This is the case in many applications. The classification of rare events is the overarching goal, e.g. in bankruptcy prediction, churn analysis or fraud detection. The problem of irrelevant variables accompanies situations where the specification of the model is not known a priori, thus in typical conditions for data mining analysts.Purpose: The purpose of this paper is to compare the combinations of the most popular strategies of handling unbalanced data with feature selection methods that represent filters, wrappers and embedded methods.Research methodology: In the empirical study, we use real datasets with additionally introduced irrelevant variables. In this way, we are able to recognize which method correctly eliminates irrelevant variables.Results: Having carried out the experiment we conclude that over-sampling does not work in connection with feature selection. Some recommendations of the most promising methods also are given.Novelty: There are many solutions proposed in the literature concerning unbalanced data as well as feature selection. The innovative field of our interests is to examine their interactions.

The Influence of Unbalanced Economic Data on Feature Selection and Quality of Classifiers

Faculty of Production Engineering and Logistic, Department of Mathematics and Applied Computer Science

Folia Oeconomica Stetinensia

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Research background: The successful learning of classifiers depends on the quality of data. Modeling is especially difficult when the data are unbalanced or...

The Influence of Unbalanced Economic Data on Feature Selection and Quality of Classifiers

Publié en ligne: 20 août 2020

Pages: 232 - 247

Reçu: 19 nov. 2019

Accepté: 31 mars 2020

DOI: https://doi.org/10.2478/foli-2020-0014

Mots clés
classifiers, class unbalance, sensitivity, feature selection, resampling

© 2020 Mariusz Kubus, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

The Influence of Unbalanced Economic Data on Feature Selection and Quality of Classifiers

Publié en ligne: 20 août 2020

Pages: 232 - 247

Reçu: 19 nov. 2019

Accepté: 31 mars 2020

DOI: https://doi.org/10.2478/foli-2020-0014

Mots clésclassifiers, class unbalance, sensitivity, feature selection, resampling

© 2020 Mariusz Kubus, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Mots clés
classifiers, class unbalance, sensitivity, feature selection, resampling