Filtering outliers to improve classification. First results

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on



Type Article in Proceedings
Conference Data a Znalosti & WIKT 2019
MU Faculty or unit

Faculty of Informatics

Web DaZ & WIKT 2019 - Zborník konferencie
Keywords Outlier Detection; Data pre-processing; Classification
Description In this work we describe preliminary experiments for exploring influence of outlier elimination to classifier accuracy. A workflow is a couple consisting of some pre-processing methods - outlier detection and filtering in our case - and a classifier. We describe a method for testing various workflows and bring first results.
Related projects: