SKC 모형을 이용한 양돈 농가의 경쟁적 벤치마킹 전략 분석

Competitive Strategies and Benchmarks for Pork Farms Using SOM+K-Means Clustering Model

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 us-ing managerial information. A major problem with statistical clustering methods 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) method-ology and demonstrate that it 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 dis-cuss a SKC model to quantify how well a topology 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.