基于AHP和PCA的多指标评价建模方法及应用

Multi-index Evaluation Modeling Method Based on AHP and PCA and Its Application

  • 摘要: 提出一种多指标评价建模方法,并以学术期刊核心竞争力评价为例对该方法进行说明验证.本建模方法针对底层指标和上层指标的特点,将主成分分析法和Softmax回归相结合用于底层评价指标权重的确定,应用层次分析法对上层指标的权重进行确定.在方法应用验证中,在分析学术期刊核心竞争力的内涵、特征和表现形式的基础上,构建了学术期刊核心竞争力评价指标体系;然后应用本方法对学术期刊核心竞争力进行评价.经验证分析可知,本评价建模方法在多指标评价情况下,具有求解简便、精确度高的优点.

     

    Abstract: This paper proposes a multi-index evaluation modeling method, and evaluation of the core competences of academic journals is used to verify the feasibility of this method. According to the characteristics of the underlying and upper indices, this modeling method is used to determine the weights of the underlying index by combining principal component analysis (PCA) and Softmax regression, and by using an analytic hierarchy process (AHP) to determine the weights of the upper index. In the application and validation of the method, which is based on analysis of the connotation, characteristics, and manifestations of the core competences of academic journals, this paper constructs an evaluation index system for such core competences. Through validation analysis, it is shown that the proposed evaluation modeling method provides the advantage of obtaining simple and highly accurate solutions in multi-index evaluation cases.

     

/

返回文章
返回