Operational analysis of k-medoids and k-means algorithms on noisy data

Clustering is applied to many applications and the decision with regards to which algorithm to use is dependent on the nature of the task to be carried out. Before choosing which clustering algorithm to use one needs to be aware of the nature of the task to be done and then determine the algorithm accordingly, based on the capabilities and performance metrics of that algorithm. This paper makes an operational comparison of the k-means and k-medoids clustering algorithms focusing on the effect of noise and outliers on each algorithm.