A Survey on K-Means Clustering for Analyzing Variation in Data

Most of the times data for certain task seems to be varying due constant changes made to method of data collection as well as due to inclusion of new parameters related to the task. This may result in false conclusion derived from data generated and might lead to failure in task or degradation in the standard of activity related to that task which is being monitored from that data. Clustering is basically the grouping of similar kind of data wherein each cluster consist of data with some similarities. Whereas most of the data is unstructured or semi-structured, and that's where unsupervised K-means Clustering method plays role to convert the data into structured one's for clustering. This paper consist of K-means clustering method which is being used to keep an eye on such variations which are occurring in data generated for a task when certain changes are incorporated in technique to track this data.