Distributed clustering using multi-tier hierarchical overlay super-peer peer-to-peer network architecture for efficient customer segmentation

Highlights：

• We propose a multi-layer hierarchical super-peer P2P network architecture to actuate the distributed clustering problem Vs. centralized Clustering.

• The proposed distributed clustering algorithm has achieved an improved in the computational speed without compromising the clustering quality or accuracy.

• The proposed architecture can be used in various types of data sets with different sizes and configuration in addition to the customer dataset used in the paper.

• The proposed architecture has been applied to various unsupervised machine learning algorithm showing its effectiveness.