Classification based on Neighborhood from Datasets with Low Quality Data

Abstract

Currently there are not many data mining method available to solve the classification task in datasets with low quality values. In this paper we propose a method of imputation/classification based on neighborhood that can work with nominal and numerical attributes which can contain low quality values. Performing a series of experiments we observe that the method not only is competitive to other similar method when working with datasets without low quality values, but it also obtains robust results when working with datasets with low quality values.