A new clustering technique is described, which is an improvement on the mountain method (MM) of clustering originally proposed by Yager and Filev. This new technique employs a data driven, hierarchical partitioning of the data set to be clustered, using a “p-tree” algorithm for spatially decomposing the data set. The centroids of data subsets in the terminal nodes of the “p-tree” become the set of candidate cluster centers upon which the iterative cluster center selection process of MM is applied. As the data dimension and/or the number of uniform grid lines used in Yager and Filev’s original technique increases, our approach requires exponentially fewer cluster centers to be evaluated by the MM selection algorithm. Extensive sample data sets are used to illustrate the performance of this new technique.