期刊名称：International Journal of Data Mining & Knowledge Management Process
印刷版ISSN：2231-007X
电子版ISSN：2230-9608
出版年度：2015
卷号：5
期号：5
页码：35
DOI：10.5121/ijdkp.2015.5503
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Interpreting available data is a focal issue in data mining. Gathering of primary data is a difficult andexpensive affair for assessing the trends for any business decision especially when multiple players arepresent. There is no uniform formula-type work procedure to deduce information from a vast data setespecially if the data formats in the secondary sources are not uniform and need enormous cleansing tomend the data for statistical analysis. In this paper, an incremental approach to cleanse data using asimple yet extended procedure is presented and it is shown how to deduce conclusions to facilitate businessdecisions. Freely available Indian Telecom Industry’s data over a year is used to illustrate this process. Itis shown how to conclude the superiority of one telecom service provider over the others comparingdifferent parameters like network availability, customer service quality etc. using a relative parameterquantification technique. It is found that this method is computationally less costly than the other knownmethods.
关键词：Quantification; Data mining; QoS; Data cleansing.
