基于数据分析与机器学习的银行贷款策略研究  

Research on bank loan strategy based on data analysis and machine learning

作　　者：杨国庆 袁椿昊 陈康耀 王艳芳[2] YANG Guoqing;YUAN Chunhao;CHEN Kangyao;WANG Yanfang(School of Computer Science and Technology and Land Information Engineering,Henan Polytechnic University,Jiaozuo 454002,China;School of Mathematics and Information Science and Land Information Engineering,Henan Polytechnic University,Jiaozuo 454002,China;School of Surveying and Mapping and Land Information Engineering,Henan Polytechnic University,Jiaozuo 454002,China)

机构地区：[1]河南理工大学计算机科学与技术学院,河南焦作454002 [2]河南理工大学数学与信息科学学院,河南焦作454002 [3]河南理工大学测绘与国土信息工程学院,河南焦作454002

出　　处：《高师理科学刊》2021年第8期27-31,共5页Journal of Science of Teachers＇College and University

基　　金：河南省教育厅优秀青年科学基金项目(202300410167);河南理工大学博士基金项目(B2017-47)。

摘　　要：综合分析企业盈利、销售、信誉等级和信贷政策等数据,利用Word2vec模型对信贷政策偏向性进行分析,利用因子分析法确定银行信贷风险指标,建立基于K-means聚类法的银行贷款策略RPC模型,确定参考贷款额度范围,并根据流失率与信誉评级以及利率之间的关系确定最佳贷款利率.运用SPSS,Python等软件求解,对山东省区域不同企业的信贷风险做出了有效的评估,并分析出合理的信贷策略.Based on the comprehensive analysis of the data of enterprise profit,sales,credit rating and credit policy, Word2 vec model was used to analyze the credit policy bias,factor analysis method was used to determine the bank credit risk index,and the RPC model of bank loan strategy was established based on K-means clustering method to determine the reference loan limit.According to the relationship between loss rate,credit rating and interest rate, the best loan interest rate is determined. By using SPSS,Python and other software,the credit risk of different enterprises in Shandong Province is effectively evaluated,and the reasonable credit strategy was given.

关 键 词：银行贷款策略 因子分析 Word2vec模型 K-means聚类法 

分 类 号：O29[理学—应用数学] F832.4[理学—数学]