摘要
银行未完全掌握中小微企业的信用评价信息是致使中小微企业融资难、融资贵的主要因素之一。针对银行对评价信息不全的中小微企业信贷决策问题,可利用随机森林算法对无信贷记录企业的信誉评级进行预测,将借贷企业的信用数据补充完整。再利用填补后的信用信息对企业的信贷风险进行量化,综合考虑风险偏好、客户流失、总收益、单位贷款风险等多种影响银行中小微企业信贷决策等因素,从而构建起考虑银行风险偏好的信贷决策模型,为银行防范中小微企业信贷风险、实现银行收益最大化等目标提供有效方法。
Banks do not completely and comprehensively grasp credit evaluation information of micro, small and medium enterprises. This is one of the main factors of difficult and expensive financing in micro, small and medium enterprises. According to the incomplete evaluation information of credit decision-making of bank for micro, small and medium enterprises, random forest algorithm can be used to predict the credit rating of enterprises without credit record and to complete credit data of credit enterprises. It is suggested to utilize filled credit information to quantize credit risk of enterprises;and comprehensively consider the influencing factors of credit decision-making of micro, small and medium enterprises, such as risk preference, customer loss, total revenue, and unit credit risks, etc. to construct credit decision-making model under the consideration of bank risk preference, and provide effective method for banks to prevent credit risk of micro, small and medium enterprises and achieve revenue maximization, etc.
作者
宫召华
邵娴
Gong Zhaohua;Shao Xian(School of Mathematics and Information Science,Shandong Technology and Business University,Yantai 264005,China;School of Statistics,Shandong Technology and Business University,Yantai 264005,China)
出处
《黑龙江科学》
2023年第1期35-40,共6页
Heilongjiang Science
基金
山东省自然基金面上项目(ZR2019MA031)。
关键词
评价信息不完全
信贷风险
信贷决策
随机森林法
Incomplete evaluation information
Credit risk quantification
Credit decision-making
Random forest algorithm
