基于Choquet模糊积分SVM集成的企业信用评估模型  

Enterprise Credit Evaluation Model Based on Choquet Fuzzy Integral SVM Integration

作　　者：张目 许素娟 Zhang Mu;Xu Sujuan(School of Big Data Application and Economics,Guizhou University of Finance and Economics,Guiyang 550025,Guizhou,China;Guizhou Institution for Technology Innovation&Entrepreneurship Investment,Guiyang 550025,Guizhou,China)

机构地区：[1]贵州财经大学大数据应用与经济学院,贵州贵阳550025 [2]贵州财经大学贵州科技创新创业投资研究院,贵州贵阳550025

出　　处：《征信》2023年第5期24-30,共7页Credit Reference

基　　金：国家自然科学基金地区项目(71861003)。

摘　　要：针对Bagging算法下基于模糊积分的SVM集成方法在企业信用评估应用中存在的不足,提出一种基于改进模糊密度-Choquet模糊积分SVM集成的企业信用评估模型。该模型借鉴Boosting算法“注重”错分样本的基本思想,考虑SVM基分类器的总体错分程度,重新定义SVM基分类器的模糊密度,实现对模糊密度的改进;在此基础上,采用Choquet模糊积分作为SVM基分类器的结合方法,从而将基于Choquet模糊积分的SVM集成方法引入到企业信用评估中。实证结果表明,与传统方法相比,该模型的预测准确率更高,第一类错误率和第二类错误率更低;精确率、召回率、F1值和Macro-F1值等分类性能指标也明显占优,说明了该模型的可行性和有效性。In view of the shortcomings of SVM integration method based on fuzzy integral under Bagging algorithm in the application of enterprise credit assessment,this paper proposes an enterprise credit evaluation model based on improved fuzzy density-Choquet fuzzy integral SVM integration.The model can draw on the basic idea of Boosting algorithm,which "pays attention to" misclassification samples,consider the overall misclassification degree of SVM base classifier,and redefine the fuzzy density of SVM base classifier to improve the fuzzy density.On this basis,the Choquet fuzzy integral is used as the combination method of SVM based classifier,so as to introduce the SVM integration method based on Choquet fuzzy integral into the enterprise credit assessment.The empirical results show that,compared with those traditional methods,the prediction accuracy of the model is higher,and the first and second kinds of error rates are lower.The classification performance indicators such as accuracy rate,recall rate,F1 value and Macro-F1 value are also obviously superior,which shows the feasibility and effectiveness of the model.

关 键 词：企业信用评估 改进模糊密度 CHOQUET模糊积分 支持向量机 集成学习 BAGGING算法 

分 类 号：F830.5[经济管理—金融学] TP391[自动化与计算机技术—计算机应用技术]