Relationship between clustering and data quality has not been thoroughly established. It is usually assumed that input dataset does not contain any errors or contains some “noise”, and this concept of “noise” is not related to any data quality concept. In this paper we focus on the four most commonly used data quality dimensions, namely accuracy, completeness, consistency and timeliness. We evaluate the impact these quality dimensions on clustering outcomes in order to find out which of them has the most negative effect. Four different clustering algorithms and five real datasets were selected to show the interaction between data quality and cluster validity.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com