基于大数据的中小微企业信贷风险评估和信贷策略研究  

Research on Credit Risk Assessment and Credit Strategy of Small,Medium and Micro Enterprises Based on Big Data

作　　者：陈春照 谢睿[1] 查婧怡 朱家明[1] Chen Chunzhao;Xie Rui;Cha Jingyi;Zhu Jiaming(Anhui University of Finance and Economics)

机构地区：[1]安徽财经大学

出　　处：《哈尔滨师范大学自然科学学报》2021年第4期20-30,共11页Natural Science Journal of Harbin Normal University

基　　金：安徽省高校人文社科研究重点项目《新时代安徽农村合作金融发展研究》(SK2018A0462);2020年国家级创新创业训练计划项目《突发公共卫生信息报告质量评价以及管理优化研究》(202010378250);安徽财经大学2021年度大学生科研创新基金《长三角城市群协同创新能力时空演变研究》(XSKY2197)。

摘　　要：针对中小微企业的信贷风险评估和信贷策略等问题,主要分为3个方面来研究.首先,针对有信誉记录的历史企业,选取有效的风险评估指标,并对其进行主成分分析和灰靶决策模型分析出是否放贷和放贷次序,然后利用风险-收益数学关系模型计算出其具体的信贷策略.其次,针对无信誉等级和违约记录的新增企业,在第一步的基础上,采用BP神经网络和二项Logistic分别预测出其信用水平,再结合基于有效前沿的贷款组合多目标优化决策模型测算出总额为1亿时的企业最优贷款投放权重,确定其信贷风险和信贷策略,旨在保证将不良贷款率控制在较低水平的同时,满足中小微企业的融资需求的力度,以实现可持续健康发展的目标.Focuses on the credit risk assessment and credit strategy of small, medium and micro enterprises, it is mainly divided into three aspects to study. First, for historical companies with creditable records, selected effective risk assessment indicators, the principal component analysis and gray target decision models are analyzed whether to lend and the sequence of lending, and then using the risk-return mathematical relationship model, their specific Credit strategy are calculated. Secondly, for new enterprises without credit rating and default records, based on the first step, the BP neural network and Binomial Logistic are used to predict their credit levels respectively, and then combined with a multi-objective optimization decision-making model based on the effective frontier loan portfolio Calculate the optimal loan placement weight of the enterprise when the total amount is 100 million, its credit risk and credit strategy are determined, which is aiming to ensure that the non-performing loan ratio is controlled at a low level, while meeting the financing needs of small, medium and micro enterprises to achieve the goal of sustainable and healthy development.

关 键 词：信贷风险 评价指标体系 PCA-GTD模型 收益-风险函数关系模型 多目标优化决策 

分 类 号：F832.4[经济管理—金融学]