Main Article Content
The problem of detection and classification of extensional inconsistencies during data integration of disparate data sources affects business competitiveness. A number of classification methods have been utilized until now, but there still some work to do in terms of effectiveness and performance. The paper shows the proposal, implementation, and evaluation of a new classification algorithm called Attribute-based Classification by Threshold that overcomes the disadvantages of the Threshold-based Classification. We have carried aout an evaluation of quality of the data matching process by comparing Threshold-based Classification, Farthest First and K-means against the proposed algorithm. The Attribute-based Classification by Threshold has a better performance than the rest of the unsupervised classification methods.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.