Parametric Comparisons of Classification Techniques in Data Mining Applications
Geeta Kashyap,  Ekta Chauhan
Data mining (DM) means to extract the hidden knowledge from large repositories of data with the use of techniques and tools. Day to day growing data in every sector which requires automatic data analysis techniques i.e. the techniques which automatically analyze the data for different perspectives and provide accurate results in terms of several parameters i.e. speed, efficiency and cost. Due to increasing interest in Data mining it become emerging research topic for research community. The various techniques of Data mining like classification, clustering can be applied to bring out hidden knowledge from the large databases. In this paper we focus on comparative analysis of different Data Mining (DM) Classification techniques for Data Mining applications i.e. in Retail Industry for Marketing Data analysis, Financial Data Analysis, Educational Data analysis as well as for the analysis of Biomedical Data. Classification is a Data Mining techniques used to predict group membership for data instance. Our research study compares the accuracy of these Classification techniques on Weka tool for Data mining applications. The compared Classification techniques and their algorithms are presented together with some experimental data that give rise to the final conclusion
Keywords- C5.O, C4.2, Decision Tree, Data Mining Applications, ID3, J48, KDD (Knowledge Discovery in Databases), Naïve Bayes, Neural Network, Weka.
Cite this Article
Geeta Kashyap,  Ekta Chauhan,   "Parametric Comparisons of Classification Techniques in Data Mining Applications"
, International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.4, Issue 2, pp.1117-1123, May 2016, Available at :http://www.ijedr.org/papers/IJEDR1602194.pdf