基于改进LSSVR的电子商务信用风险评估  

E-commerce credit risk assessment based on improved LSSVR

作　　者：张泉[1] 曹洁[1] ZHANG Quan;CAO Jie(Chuzhou Polytechnic,Chuzhou 239000,Anhui,China)

机构地区：[1]滁州职业技术学院,安徽滁州239000

出　　处：《贵阳学院学报（自然科学版）》2023年第1期1-4,31,共5页Journal of Guiyang University：Natural Sciences

基　　金：“数字经济时代安徽省产业结构与消费结构循环升级机制研究”(项目编号:SK2021ZD0107)。

摘　　要：由于电子商务具备诸多新型的产业特征,而现有的风险识别工具关注传统行业的产业发展,无法有效地评估电子商务这一新兴产业的风险情况。为防备电子商务企业可能出现的信用风险,提出了一个基于支持向量机的LSSVR风险识别模型,并采用我国18家上市电子商务企业的数据进行了实证分析。结果表明,该方法具备较强的实践价值和风险预测能力,相较于传统LSSVR方法计算速度更快,所需参数更少,能够提升电子商务信用风险的评价效率。Because e-commerce has many new industrial characteristics,and the existing risk identification tools focus on the industrial development of traditional industries,it is unable to effectively evaluate the risk situation of e-commerce,an emerging industry.In order to prevent the possible credit risk of e-commerce enterprises,a LSSVR risk identification model based on support vector machine is proposed,and the data of 18 listed e-commerce enterprises in China are used for empirical analysis.The results show that this method has strong practical value and risk prediction ability.Compared with the traditional LSSVR method,it has faster calculation speed,less parameters required,and can improve the evaluation efficiency of e-commerce credit risk.

关 键 词：电子商务信用风险 风险识别 LSSVR模型 

分 类 号：F224[经济管理—国民经济]