21st Century has marked high velocity of data generation not only in terms of size but also in variety. Analyzing large data sets with different forms is also a challenging task. Data Mining is regarded as efficient method to extract meaningful information as per user requirements. But considering the size of modern data, traditional data mining techniques are failing. Clustering can be regarded as one of the most important technique to mine the data by splitting large data sets into clusters. The paper’s primary contribution is to provide comprehensive analysis of Big Data Clustering algorithms on basis of: Partitioning, Hierarchical, Density, Grid and Model. In addition to this, performance comparison of algorithms is performed on basis of volume, variety and velocity.
Big data, Clustering, Clustering algorithms, Partitioning-based clustering, Grid-Based clustering, Hierarchical clustering, Density-based clustering, Model based clustering, Data mining.