Imputation of Missing Data:A Semi-Supervised Clusteringmethodology

摘要

Data mining is being applied with success in different fields of humanendeavor including Marketing, Customer Relationship Management andHealthcare. Real world data sets are always accompanied by missing data, amajor factor affecting data quality. Missing data has been a pervasive prob-lem in data analysis since the origin of data collection. In the knowledgediscovery process, missing data introduces bias in the model evaluation and