*Corresponding author:

A b s t r a c t K-means clustering algorithms are widely used for many practical applications. Original k-mean algorithm select initial centroids and medoids randomly that affect the quality of the resulting clusters and sometimes it generates unstable and empty clusters which are meaningless. The original k-means algorithm is computationally expensive and requires time proportional to the product of the number of data items, number of clusters and the number of iterations. The new approach for the k-mean algorithm eliminates the deficiency of exiting k mean. It first calculates the initial centroids k as per requirements of users and then gives better, effective and good cluster without scarifying Accuracy. It generates stable clusters to improve accuracy. It also reduces the mean square error and improves the quality of clustering. We also applied our algorithm for the evaluation of studentÊs academic performance for the purpose of making effective decision by the student councilors