Clustering Evaluation Methods based on Multiple Attribute Decision Making

Cluster analysis has been widely used in many fields since its appearance, and the validation method of clustering has received much less attention. In fact, the quality evaluation of clustering results is also a crucial link in the whole clustering process. Clustering validation are generally divided into external clustering validation, internal clustering validation and relative cluster validation. This paper studies the external clustering validation method. Firstly, the article selects several different categories of clustering verification methods. At the same time, the article introduces the Maclaurin symmetric mean (MSM) operator and multiple attribute decision making (MADM) method. Finally, an optimal clustering algorithm selection model for a certain data set can be obtained. The experimental results show that the proposed method can select the corresponding optimal algorithm for inhomogeneity data sets.