Paper Details

Data mining is an area where computer science, machine learning and statistics meet and where the goal is todiscover and extract information such as relations and patterns that’s hidden inside the data. The volume of data isincreasing exponentially and analyzing such a large volume of data has become one of the big challenges for IT industries.The data has become the asset of every enterprise. The mining of such large volume of data provides the valuableinformation regarding to the specific field for which data are collected. There are many types of data mining techniquesavailable and used to extract the valuable hidden patterns from the large volume of data. The patterns extracted from thedata become the part of knowledge base for the decision support system. The main goal of the data mining is to find out therelevant and more valuable information from the data and building the knowledge base. In this paper we are considering theK-means Clustering algorithm for classifying the data on the basis of similarity. This is one type of the unsupervised machinelearning technique. The Clusters produced by the K-means clustering are further classified using Supervised machinelearning techniques, Such as K-nearest Neighbour method and decision tree algorithm.

Vaibhav Sharma, Shrwan Ram, “Comparative Study of K-Nearest Neighbor Classification and J48 Decision Tree Algorithm with and without Clustering Considering Different Data Parameters”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 4, Issue 8, pp. 460-466, August 2017.