Customer segmentation using the self-organizing map and its variants

Researcher: Mufunwa Nemushungwa, University of the Witwatersrand, Johannesburg
Supervisor: Dr Martins Arasomwan, University of the Witwatersrand, Johannesburg

This research compares three variations of SOM: standard SOM, SOM combined with K-means, and SOM paired with the social spider optimization (SSO) algorithm in performing customer segmentation. The results show that combined SOM with SSO algorithm outperforms the the paired SOM and K-means in
enhancing the SOM clustering performance.dress road damage problems.