中小微企业信贷策略研究  

The Study on Credit Strategy for MSMEs

作　　者：王志勇[1] 杨旭[2] 吴嘉津 WANG Zhiyong;YANG Xu;WU Jiajin(School of Mathematical Sciences,University of Electronic Science and Technology of China,Chengdu,Sichuan 610731,China;School of Computer Science and Technology,Xi’an Jiaotong University,Xi’an,Shaanxi 710049,China;School of Computer Science and Engineering,University of Electronic Science and Technology of China,Chengdu,Sichuan 610731,China)

机构地区：[1]电子科技大学数学科学学院,四川成都610731 [2]西安交通大学计算机科学与技术学院,陕西西安710049 [3]电子科技大学计算机科学与工程学院,四川成都610731

出　　处：《数学建模及其应用》2021年第1期80-91,共12页Mathematical Modeling and Its Applications

摘　　要：利用中小微企业的进销项发票数据,对中小微企业的信贷风险进行评估,并给出最优贷款策略.首先,建立了企业实力-信誉指标体系,并通过优化模型得到有信誉等级和违约记录的123家企业的最优贷款策略;然后,应用WOE-Logistic评分卡模型对无信誉等级的302家企业进行信誉评级,通过上述实力-信誉指标体系和优化模型得到最优贷款策略;最后,针对不同性质的突发事件建立了通用的风险量化模型,并以新冠疫情为例,分析了其对不同行业的积(消)极影响,并得到上述302家企业新的最优贷款策略.This paper evaluates the credit risk of MSMEs(Micro,small,and medium enterprises)by using the data of purchase invoice and sales invoice of MSMEs(Micro,small,and medium enterprises),and provides the optimal credit strategy.Firstly,the enterprise strength-reputation index system is established,and the optimal credit strategy for 123 enterprises with credit rating and default record is obtained basing on the optimization model.Then,the WoE-Logistic credit score card model is applied to 302 enterprises without credit rating.Furthermore,we develop the former models taking unexpected events into account.Finally,we investigate the positive(negative)influence for different industries in COVID-19 and obtain the new optimal credit strategy for the 302 enterprises.

关 键 词：信用贷款 非线性规划 K-MEANS聚类 LOGISTIC回归 对数正态分布 

分 类 号：O29[理学—应用数学]