摘要
针对企业的信用评估,基于已有研究,引入企业财务指标和非财务指标,使用机器学习分类方法构建信用评估模型,并对几种方法的分类准确率进行了比较分析.实验结果表明,该信用评估指标体系可行,随机森林方法在该指标体系上的分类效果最好.同时,优化了分类效果较差的多层感知器,提升了分类准确率.
As for enterprise credit evaluation,this paper introduces financial indexes and non-financial indexes based on previous research.Machine learning classification methods are used to build credit evaluation models,and the classification accuracy rates of several methods are compared and analyzed.The experimental results show that the credit evaluation index system is feasible,and that the random forest method has the best classification effect on the index system.At the same time,the multi-layer perceptron with poor classification effect is optimized,and the classification accuracy is improved.
作者
朱菁婕
吴怀岗
Zhu Jingjie;Wu Huaigang(School of Computer Science and Technology,Nanjing Normal University,Nanjing 210023,China)
出处
《南京师范大学学报（工程技术版）》
CAS
2020年第3期81-86,共6页
Journal of Nanjing Normal University(Engineering and Technology Edition)
关键词
企业信用评估
信用指标体系
信用评估模型
enterprise credit evaluation
credit index system
credit evaluation model
