Header

UZH-Logo

Maintenance Infos

The effect of missing data on classification quality


Feldman, Michael; Even, Adir; Parmet, Yisrael (2012). The effect of missing data on classification quality. In: 17th International Conference on Information Quality, Paris, France, 15 November 2012 - 17 November 2012, 229-242.

Abstract

The field of data quality management has long recognized the negative impact of data quality defects on decision quality. In many decision scenarios, this negative impact can be largely attributed to the mediating role played by decision-support models - with defected data, the estimation of such a model becomes less reliable and, as a result, the likelihood of flawed decisions increases. Drawing on that argument, this study presents a methodology for assessing the impact of quality defects on the likelihood of flawed decisions. The methodology is first presented at a high level, and then extended for analyzing the impact of missing values on binary Linear Discriminant Analysis (LDA) classifiers. To conclude, we discuss possible directions for extensions and future directions.

Abstract

The field of data quality management has long recognized the negative impact of data quality defects on decision quality. In many decision scenarios, this negative impact can be largely attributed to the mediating role played by decision-support models - with defected data, the estimation of such a model becomes less reliable and, as a result, the likelihood of flawed decisions increases. Drawing on that argument, this study presents a methodology for assessing the impact of quality defects on the likelihood of flawed decisions. The methodology is first presented at a high level, and then extended for analyzing the impact of missing values on binary Linear Discriminant Analysis (LDA) classifiers. To conclude, we discuss possible directions for extensions and future directions.

Statistics

Downloads

55 downloads since deposited on 04 Mar 2014
11 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:17 November 2012
Deposited On:04 Mar 2014 14:08
Last Modified:26 Aug 2017 00:08
Publisher:Conservatioire national des arts et métiers
Free access at:Official URL. An embargo period may apply.
Official URL:http://mitiq.mit.edu/ICIQ/2012/2012%20ICIQ%20CDproceedings%20final.pdf
Related URLs:http://iciq2012.cnam.fr/
Other Identification Number:merlin-id:9029

Download

Download PDF  'The effect of missing data on classification quality'.
Preview
Content: Published Version
Filetype: PDF
Size: 496kB