Preparing Low Cost Solution Based On Customized Process Of Parallel Clustering Solution

Abstract

Big Data analysis is the field of data processing where it involves collections of large volume of data sets which are generally so large and really complex in nature and also there is no unified scientific solution globally for any data analysis due to its nature of difficulties to process them by adopting traditional approaches and technologies. Handling large volume of data and preparing them for deep analysis to evaluate them and prepare required information as required by the mining process is the most complex and sometimes costlier task in real-time. There are many solutions for the data mining process like clustering, special mining, k-means mining to name a few. But the real challenge in data mining process is choosing the correct solution or algorithm to apply for mining the input data and tuning the processing step in such a way that we establish a cost effective solution for the entire mining process. There may be many solutions where mining is efficient but cost of operation is not effective and sometimes it is vice-versa. Hence there is always an ever increasing demand for an efficient solution which is cost effective as well as efficient in data mining technique. The intent of this paper is researching on how we implement a concept called Parallel clustering which gives higher benefit in terms of cost and time in data mining processing without compromising the efficiency and accuracy in expected result. This paper discusses one such custom algorithm and its performance as compared to other solutions.