摘要
企业的信用量化评级是影响金融市场资金流向和借贷成本的重要因素。研究中小微企业信贷风险的量化问题。对于有信贷记录的企业,将有效发票占比、实际利润、进货总额、未违约率作为4个要素,建立基于层次分析法的企业信贷风险量化模型,得到了企业的信用评分;对于无信贷记录的企业,建立神经网络模型预测其未违约率,量化分析了信贷风险。研究结果为银行制定信贷策略提供了理论支撑。
In the financial market,quantifying the enterprise credit is an important factor for the capital flow and borrowing cost.The quantitative problem of credit risk for small,medium and micro-sized enterprises is investigated.For the enterprises with credit records,based on Analytic Hierarchy Process the enterprise credit risk quantification model is established by taking the proportion of valid invoice,actual profit,total amount of purchased goods and non-default rate as four elements,and the credit score of the enterprise is obtained.For the enterprises without credit records,their non-default rates are predicted by a neural network model,and their credit risk is quantitatively analyzed.The results provide a theoretical support for banks to formulate credit strategies.
作者
白羽
三郎斯基
王晓妍
孙少飞
王恒友
BAI Yu;SANLANG Siji;WANG Xiaoyan;SUN Shaofei;WANG Hengyou(School of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044;School of Geomatics and Urban Spatial Information, Beijing University of Civil Engineering and Architecture, Beijing 100044;School of Urban Economics and Management, Beijing University of Civil Engineering and Architecture, Beijing 100044;Beijing Key Laboratory of Functional Materials for Building Structure and Environment Remediation, Beijing University of Civil Engineering and Architecture, Beijing 10004)
出处
《北京建筑大学学报》
2021年第2期93-97,共5页
Journal of Beijing University of Civil Engineering and Architecture
基金
国家自然科学基金项目(62072024)
北京市属高校基本科研业务费专项资金项目(X20142)。
关键词
信贷风险
量化
层次分析法
神经网络模型
credit risk
quantification
Analytic Hierarchy Process
neural network model