Imputation of Missing Values using Improved K-Means Clustering Algorithm to Attain Data Quality

Abstract

A data warehouse aids in the management of large amounts of data that may be stored in order to handle user input during the computer process. The major issue with a data warehouse is to maintain the data that the user stores in good quality. Some traditional techniques can improve data quality while also increasing efficiency. Each unit of data has a unique feature that has been researched by many researchers and has an influence on data quality. This research article has enhanced the K-Means method by utilizing the Euclidean Distance metric to detect missing values from the gathered sources and replace them with closest values while maintaining the data's consistency, exactness, and quality. yThe improved data will assist developers in analysing data quality prior to data integration by allowing them to make informed decisions quickly in accordance with business requirements. Improved K-Means achieves better accuracy and requires less computational time for clustering data objects when compared to other related approaches.