K-Means++ Clustering Using MapReduce Framework for Large Datasets

Clustering techniques are important to analyze the data due to the heavy increase of data in modern investigation. In real world these techniques are mostly used in many domains, some of them are financial analysis, social networks, digital marketing, etc. To support clustering over large scale datasets, public cloud infrastructure will play the major role for presentation of the data and financial trades. In our work, MapReduce based K-means++ clustering technique is proposed to allow the better grouping of data into appropriate clusters. The results of the paper denote that the present algorithm can efficiently process large amount of data.