Evaluation of clusterings - Metrics and visual support

Elke Achtert*, Sascha Goldhofer, Hans Peter Kriegel, Erich Schubert, Arthur Zimek

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

When comparing clustering results, any evaluation metric breaks down the available information to a single number. However, a lot of evaluation metrics are around, that are not always concordant nor easily interpretable in judging the agreement of a pair of clusterings. Here, we provide a tool to visually support the assessment of clustering results in comparing multiple clusterings. Along the way, the suitability of a couple of clustering comparison measures can be judged in different scenarios.

Original languageEnglish
Title of host publicationProceedings of the 2012 IEEE 28th International Conference on Data Engineering
PublisherIEEE
Publication date30. Jul 2012
Pages1285-1288
ISBN (Print)978-1-4673-0042-1
ISBN (Electronic)978-0-7695-4747-3
DOIs
Publication statusPublished - 30. Jul 2012
Externally publishedYes
EventIEEE 28th International Conference on Data Engineering - Arlington, United States
Duration: 1. Apr 20125. Apr 2012

Conference

ConferenceIEEE 28th International Conference on Data Engineering
CountryUnited States
CityArlington
Period01/04/201205/04/2012
SponsorMicrosoft, National Science Foundation (NSF), EMC, Greenplum, IBM Research
SeriesProceedings - International Conference on Data Engineering
ISSN1084-4627

Cite this

Achtert, E., Goldhofer, S., Kriegel, H. P., Schubert, E., & Zimek, A. (2012). Evaluation of clusterings - Metrics and visual support. In Proceedings of the 2012 IEEE 28th International Conference on Data Engineering (pp. 1285-1288). IEEE. Proceedings - International Conference on Data Engineering https://doi.org/10.1109/ICDE.2012.128
Achtert, Elke ; Goldhofer, Sascha ; Kriegel, Hans Peter ; Schubert, Erich ; Zimek, Arthur. / Evaluation of clusterings - Metrics and visual support. Proceedings of the 2012 IEEE 28th International Conference on Data Engineering. IEEE, 2012. pp. 1285-1288 (Proceedings - International Conference on Data Engineering).
@inproceedings{4428623d558c470293c8054d2b9963da,
title = "Evaluation of clusterings - Metrics and visual support",
abstract = "When comparing clustering results, any evaluation metric breaks down the available information to a single number. However, a lot of evaluation metrics are around, that are not always concordant nor easily interpretable in judging the agreement of a pair of clusterings. Here, we provide a tool to visually support the assessment of clustering results in comparing multiple clusterings. Along the way, the suitability of a couple of clustering comparison measures can be judged in different scenarios.",
author = "Elke Achtert and Sascha Goldhofer and Kriegel, {Hans Peter} and Erich Schubert and Arthur Zimek",
year = "2012",
month = "7",
day = "30",
doi = "10.1109/ICDE.2012.128",
language = "English",
isbn = "978-1-4673-0042-1",
series = "Proceedings - International Conference on Data Engineering",
publisher = "IEEE",
pages = "1285--1288",
booktitle = "Proceedings of the 2012 IEEE 28th International Conference on Data Engineering",
address = "United States",

}

Achtert, E, Goldhofer, S, Kriegel, HP, Schubert, E & Zimek, A 2012, Evaluation of clusterings - Metrics and visual support. in Proceedings of the 2012 IEEE 28th International Conference on Data Engineering. IEEE, Proceedings - International Conference on Data Engineering, pp. 1285-1288, IEEE 28th International Conference on Data Engineering, Arlington, United States, 01/04/2012. https://doi.org/10.1109/ICDE.2012.128

Evaluation of clusterings - Metrics and visual support. / Achtert, Elke; Goldhofer, Sascha; Kriegel, Hans Peter; Schubert, Erich; Zimek, Arthur.

Proceedings of the 2012 IEEE 28th International Conference on Data Engineering. IEEE, 2012. p. 1285-1288 (Proceedings - International Conference on Data Engineering).

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Evaluation of clusterings - Metrics and visual support

AU - Achtert, Elke

AU - Goldhofer, Sascha

AU - Kriegel, Hans Peter

AU - Schubert, Erich

AU - Zimek, Arthur

PY - 2012/7/30

Y1 - 2012/7/30

N2 - When comparing clustering results, any evaluation metric breaks down the available information to a single number. However, a lot of evaluation metrics are around, that are not always concordant nor easily interpretable in judging the agreement of a pair of clusterings. Here, we provide a tool to visually support the assessment of clustering results in comparing multiple clusterings. Along the way, the suitability of a couple of clustering comparison measures can be judged in different scenarios.

AB - When comparing clustering results, any evaluation metric breaks down the available information to a single number. However, a lot of evaluation metrics are around, that are not always concordant nor easily interpretable in judging the agreement of a pair of clusterings. Here, we provide a tool to visually support the assessment of clustering results in comparing multiple clusterings. Along the way, the suitability of a couple of clustering comparison measures can be judged in different scenarios.

U2 - 10.1109/ICDE.2012.128

DO - 10.1109/ICDE.2012.128

M3 - Article in proceedings

AN - SCOPUS:84864208710

SN - 978-1-4673-0042-1

T3 - Proceedings - International Conference on Data Engineering

SP - 1285

EP - 1288

BT - Proceedings of the 2012 IEEE 28th International Conference on Data Engineering

PB - IEEE

ER -

Achtert E, Goldhofer S, Kriegel HP, Schubert E, Zimek A. Evaluation of clusterings - Metrics and visual support. In Proceedings of the 2012 IEEE 28th International Conference on Data Engineering. IEEE. 2012. p. 1285-1288. (Proceedings - International Conference on Data Engineering). https://doi.org/10.1109/ICDE.2012.128