Extending Bagging for Imbalanced Data

Jerzy Błaszczyński; Jerzy Stefanowski; Łukasz Idkowiak

doi:10.1007/978-3-319-00969-8_26

Scientific Information System of the Poznań University of Technology

PL EN

Main page / Publications / Extending Bagging for Imbalanced Data

Submit a comment

Chapter

Download BibTeX

Title

Extending Bagging for Imbalanced Data

Authors

Jerzy Błaszczyński (WI) ^{[ 1 ][ P ]}
Jerzy Stefanowski (WI) ^{[ 1 ][ P ]}
Łukasz Idkowiak

^{[ 1 ]} Instytut Informatyki, Wydział Informatyki, Politechnika Poznańska | ^{[ P ]} employee

Year of publication

2013

Chapter type

paper

Publication language

english

Abstract

EN Various modifications of bagging for class imbalanced data are discussed. An experimental comparison of known bagging modifications shows that integrating with undersampling is more powerful than oversampling. We introduce Local-and-Over-All Balanced bagging where probability of sampling an example is tuned according to the class distribution inside its neighbourhood. Experiments indicate that this proposal is competitive to best undersampling bagging extensions.

Pages (from - to)

269 - 278

DOI

10.1007/978-3-319-00969-8_26

URL

https://link.springer.com/chapter/10.1007/978-3-319-00969-8_26

Book

Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013

Presented on

8th International Conference on Computer Recognition Systems, CORES 2013, 27-29.05.2013, Milków, Poland

Publication indexed in

WoS (15)

System created by Poznań University of Technology and Poznan Supercomputing and Networking Center

Log in through eKonto to add to SIS