Download | - View accepted manuscript: Robustness of classifiers to changing environments (PDF, 301 KiB)
|
---|
DOI | Resolve DOI: https://doi.org/10.1007/978-3-642-13059-5_23 |
---|
Author | Search for: Abbasian, Houman; Search for: Drummond, Chris1; Search for: Japkowicz, Nathalie; Search for: Matwin, Stan |
---|
Affiliation | - National Research Council of Canada. NRC Institute for Information Technology
|
---|
Format | Text, Book Chapter |
---|
Conference | 23rd Canadian Conference on Artificial Intelligence (Canadian AI 2010), May 31-June 2, 2010, Ottawa, Ontario, Canada |
---|
Subject | classifier evaluation; changing environments; classifier robustness |
---|
Abstract | In this paper, we test some of the most commonly used classifiers to identify which ones are the most robust to changing environments. The environment may change over time due to some contextual or definitional changes. The environment may change with location. It would be surprising if the performance of common classifiers did not degrade with these changes. The question, we address here, is whether or not some types of classifier are inherently more immune than others to these effects. In this study, we simulate the changing of environment by reducing the in uence on the class of the most significant attributes. Based on our analysis, K-Nearest Neighbor and Artificial Neural Networks are the most robust learners, ensemble algorithms are somewhat robust, whereas Naive Bayes, Logistic Regression and particularly Decision Trees are the most affected. |
---|
Publication date | 2010-06-02 |
---|
Publisher | Springer Berlin Heidelberg |
---|
In | |
---|
Series | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
NPARC number | 15336798 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 77119b1a-8896-465f-a80f-d201f5f789d8 |
---|
Record created | 2010-06-10 |
---|
Record modified | 2020-03-03 |
---|