Cluster Analysis in Data Mining using K-Means Method

Abstract

To find the unknown and hidden pattern from large amount of data of insurance organizations. There are strong customer base required with the help of large database. Cluster Analysis is an excellent statistical tool for a large and multivariate database. The clusters analysis with K-Means method may be used to develop the model which is useful to find the relationship in a database. In this paper, consider the data of LIC customer, the seeds are the first three customers then compute the distance from cluster using the attributes of customers with the help of Clustering with K-Means method. Comparing the mean distance of cluster with the seeds. Finally, we find the nigh distances from the cluster as the cluster (C1) have three customers named S1, S2, S10 which are satisfy with all the benefits, terms and conditions of cluster (C1). If requirements of any customer same as the S1, S2, S10 then we allocated the cluster (C1). It will increase the revenue as well as profit of the organization with customer satisfaction.