基于遗传算法的多级层次分析法在企业风险评估中的应用研究

Research on application of multi level analytic hierarchy process based on genetic algorithm in enterprise risk assessment

随着市场主体数量的迅速增长,国家市场监督管理总局提出在3年内全面落实企业信用风险分类管理。多级层次分析法的企业风险评估算法是基于层次分析法的改进,以山东省市场主体数据为例,根据企业信用风险分类指标设定三级评价指标,建立层次分析模型,并采用遗传算法对模型中的多个指标参数进行最优值求解。该方法结合定量分析与定性分析,通过分析各目标在整体中的重要程度,给出每个属性的权重,并计算出各属性的优劣排序。研究结果表明,多级层次分析法能够有效解决企业风险评估的复杂问题。

With the rapid growth of the number of market entities,the State Administration for Market Regulation has proposed to strive for the comprehensive implementation of enterprise credit risk classification management within three years.The enterprise risk assessment algorithm of multilevel analytic hierarchy process is based on the improvement of analytic hierarchy process.Taking the market entity data in Shandong Province as an example,three-level evaluation indicators are set according to the enterprise credit risk classification indicators,and an analytic hierarchy process model is established.Genetic algorithm is used to solve the optimal values of multiple indicator parameters in the model.This method combines quantitative analysis and qualitative analysis,by analyzing the importance of each target in the overall picture,giving the weight of each attribute,and calculating the ranking of the advantages and disadvantages of each attribute.The research results indicate that the multi-level analytic hierarchy process can effectively solve the complex problems of enterprise risk assessment.