A New Cluster Decision Analysis Study based on EWM and Combined Regression Analysis

In the context of the development of data science and big data technology, decision analysis has become quite important in many fields. In particular, in business management, financial market analysis, and the formulation of public policies, how to effectively analyze and make use of a large amount of data to make scientific and rational decisions has become an urgent problem. In these regards, cluster analysis is an important method of statistical analysis that helps a decision-maker get a better understanding of the structure of the data or patterns by organizing them into clusters in which objects that belong to the same cluster are similar to each other and much different from those that form other clusters. However, traditional clustering methods basically rely on single statistical or machine learning models, which often results in limitations and instability in the outcomes. Therefore, combining multiple methods to improve accuracy and reliability in decision analysis is a current research focus. In this respect, a new cluster decision analysis method is proposed in the present study, one that combines the Entropy Weight Method with combined regression analysis. The Entropy Weight Method is an objective weighting method aimed at determining the weights of indicators; it is very effective in reflecting variability and information content in every indicator. Combined regression analysis joins powers of these various regression models to be more pervasive and accurate in understanding relationships between variables. One can, therefore, fine-tune the precision of cluster analysis by such combined methodology and at the same time, enhance the interpretability and practicality of results. It will build up this new approach and apply it to the deep data analysis of certain fields, verifying the effectiveness and superiority of the application, and providing more scientific and reliable analytical tools for related decision-makers to make decisions in complex environments.