Cluster Analysis Using Ensemble ROCK Method in District/City Grouping in South Sulawesi Province based on People's Welfare Indicators

Cluster analysis is a data mining technique used to group based on the similarity of attributes object data. One problems that are often encountered in cluster with mixed categorical and numerical scale. The clustering stage for using ensemble ROCK (Robust Clustering links) method carried out by combining outputs from numeric scale Hierarchical Agglomerative method. best determined criteria ratio between standard deviations within (SW) smallest deviation groups (SB). Based 24 observation objects regencies cities Province South Sulawesi, value 0.1 produces three clusters 2,27 x10-16 combination output results