CCCS: A top-down associative classifier for imbalanced class distribution

Bavani Arunasalam, Sanjay Chawla

Research output: Chapter in Book/Report/Conference proceedingConference contribution

37 Citations (Scopus)

Abstract

In this paper we propose CCCS, a new algorithm for classification based on association rule mining. The key innovation in CCCS is the use of a new measure, the "Complement Class Support (CCS)" whose application results in rules which are guaranteed to be positively correlated. Furthermore, the anti-monotonic property that CCS possesses has very different semantics vis-a-vis the traditional support measure. In particular, "good" rules have a low CCS value. This makes CCS an ideal measure to use in conjunction with a top-down algorithm. Finally, the nature of CCS allows the pruning of rules without the setting of any threshold parameter! To the best of our knowledge this is the first threshold-free algorithm in association rule mining for classification.

Original languageEnglish
Title of host publicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Pages517-522
Number of pages6
Volume2006
Publication statusPublished - 2006
Externally publishedYes
EventKDD 2006: 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - Philadelphia, PA, United States
Duration: 20 Aug 200623 Aug 2006

Other

OtherKDD 2006: 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
CountryUnited States
CityPhiladelphia, PA
Period20/8/0623/8/06

Fingerprint

Classifiers
Association rules
Innovation
Semantics

Keywords

  • Association Rules Mining
  • Classification
  • Imbalanced Data sets
  • Parameter-free mining

ASJC Scopus subject areas

  • Information Systems

Cite this

Arunasalam, B., & Chawla, S. (2006). CCCS: A top-down associative classifier for imbalanced class distribution. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Vol. 2006, pp. 517-522)

CCCS : A top-down associative classifier for imbalanced class distribution. / Arunasalam, Bavani; Chawla, Sanjay.

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2006 2006. p. 517-522.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Arunasalam, B & Chawla, S 2006, CCCS: A top-down associative classifier for imbalanced class distribution. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. vol. 2006, pp. 517-522, KDD 2006: 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, United States, 20/8/06.
Arunasalam B, Chawla S. CCCS: A top-down associative classifier for imbalanced class distribution. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2006. 2006. p. 517-522
Arunasalam, Bavani ; Chawla, Sanjay. / CCCS : A top-down associative classifier for imbalanced class distribution. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2006 2006. pp. 517-522
@inproceedings{79d97cfa1d8e49e0bb487a7f957f8b67,
title = "CCCS: A top-down associative classifier for imbalanced class distribution",
abstract = "In this paper we propose CCCS, a new algorithm for classification based on association rule mining. The key innovation in CCCS is the use of a new measure, the {"}Complement Class Support (CCS){"} whose application results in rules which are guaranteed to be positively correlated. Furthermore, the anti-monotonic property that CCS possesses has very different semantics vis-a-vis the traditional support measure. In particular, {"}good{"} rules have a low CCS value. This makes CCS an ideal measure to use in conjunction with a top-down algorithm. Finally, the nature of CCS allows the pruning of rules without the setting of any threshold parameter! To the best of our knowledge this is the first threshold-free algorithm in association rule mining for classification.",
keywords = "Association Rules Mining, Classification, Imbalanced Data sets, Parameter-free mining",
author = "Bavani Arunasalam and Sanjay Chawla",
year = "2006",
language = "English",
isbn = "1595933395",
volume = "2006",
pages = "517--522",
booktitle = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

}

TY - GEN

T1 - CCCS

T2 - A top-down associative classifier for imbalanced class distribution

AU - Arunasalam, Bavani

AU - Chawla, Sanjay

PY - 2006

Y1 - 2006

N2 - In this paper we propose CCCS, a new algorithm for classification based on association rule mining. The key innovation in CCCS is the use of a new measure, the "Complement Class Support (CCS)" whose application results in rules which are guaranteed to be positively correlated. Furthermore, the anti-monotonic property that CCS possesses has very different semantics vis-a-vis the traditional support measure. In particular, "good" rules have a low CCS value. This makes CCS an ideal measure to use in conjunction with a top-down algorithm. Finally, the nature of CCS allows the pruning of rules without the setting of any threshold parameter! To the best of our knowledge this is the first threshold-free algorithm in association rule mining for classification.

AB - In this paper we propose CCCS, a new algorithm for classification based on association rule mining. The key innovation in CCCS is the use of a new measure, the "Complement Class Support (CCS)" whose application results in rules which are guaranteed to be positively correlated. Furthermore, the anti-monotonic property that CCS possesses has very different semantics vis-a-vis the traditional support measure. In particular, "good" rules have a low CCS value. This makes CCS an ideal measure to use in conjunction with a top-down algorithm. Finally, the nature of CCS allows the pruning of rules without the setting of any threshold parameter! To the best of our knowledge this is the first threshold-free algorithm in association rule mining for classification.

KW - Association Rules Mining

KW - Classification

KW - Imbalanced Data sets

KW - Parameter-free mining

UR - http://www.scopus.com/inward/record.url?scp=33749576324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749576324&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33749576324

SN - 1595933395

SN - 9781595933393

VL - 2006

SP - 517

EP - 522

BT - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

ER -