Now days the environment produces large amount of data which is needed to be analysed,stored and secured in an efficient way. If we use BIG DATA efficiently,it can solve tremendous amount of problems. For analysis of big data the concept of Data Miningalong with the concept of machine learning is used. In this paper we are going to discuss on how to use parallel k-means algorithm and the adaptive k-means algorithm which reduces the iterations to cluster in big data,but time complexity of classic k-means algorithm is always high in large data sets. We have implemented an algorithm which is the fusion of parallel k-means algorithm with reducing the number of iterations. For our implementation we took prone accidental zones data set because life is more important than everything.We will also discuss about the applications of this algorithm that are used in real time environment. Last but not least this thesis will also discuss the various issues and future challenges in BIG DATA environment. © 2016,International Journal of Pharmacy and Technology. All rights reserved.