This paper sets out to determine the strategic positioning of pork farms, using data surveyed and evaluated from the pork farms diagnosis model of RDA. Its starting point is the idea of the strategic group, regularly employed in operation management to explain the relationship between farms within the same group, but with the characteristic that the strategic group is identified using managerial information. A major problem with statistical clustering method used today is the tendency for classification errors to occur when the empirical data departs from the ideal conditions of compact isolated clusters. We use a combined SOM+K-means clustering(SKC) methodology and demonstrate that is superior to the individual SOM and K-means cluster method. As the exploratory data analysis technique used to obtain these strategic group, we present and discuss a SKC model to quantify how well a topolgy preserving mapping algorithm maps the high-dimensional input data onto the neural network structure. The results of the study indicates that by using the SKC model, we are able to structure, classify, and visualize large amounts of multidimensional diagnosis data of pork farms in a meaningful manner.