Data Cleaning Framework: An Extensible Approach to Data Cleaning

The growing dependence of society on enormous quantities of information stored electronically has led to a corresponding rise in errors in this information. The stored data can be critically important, necessitating new ways of correcting anomalous records. Current cleaning techniques are very domain-specific and hard to extend, hindering their use in some areas. This work proposes an extensible framework for data cleaning, allowing users to customize the cleaning to their specific requirements. It defines categories of common cleaning operations, allowing more robust support for user-implemented cleaning functions in these categories. The experimental results show that the proposed data cleaning framework is an effective approach to cleaning data for arbitrary domains.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2011

Author dc:creator

• Gu, Randy S.

Contributors dc:contributor

• Chang, Kevin C-C.

• Data Cleaning

Statement dc:rights

• Copyright 2010 Randy Siran Gu

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/18304

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/18304