供应链金融大数据分布特征的分析与洞见  

Big Data Analytics and Insights in Distribution Characteristics of Supply Chain Finance

作　　者：刘颖 LIU Ying(School of Management Science and Information Engineering,Jilin University of Finance and Economics,Changchun 130117,China;Jilin Province Key Laboratory of Logistics Industry Economy and Intelligent Logistics,Changchun 130117,China;Laboratory of Internet Finance,Jilin University of Finance and Economics,Changchun 130117,China)

机构地区：[1]吉林财经大学管理科学与信息工程学院,长春130117 [2]吉林省物流产业经济与智能物流重点实验室,长春130117 [3]吉林财经大学互联网金融重点实验室,长春130117

出　　处：《计算机科学》2019年第2期1-10,共10页Computer Science

基　　金：吉林省科技厅自然基金(20180101337JC);国家自然科学基金(61402193;61806082);长春市地院(校;所)合作项目(17DY009);物流产业经济与智能物流吉林省高校重点实验室开放基金(201702)资助

摘　　要：半结构、非结构化、海量的供应链金融数据使得大数据环境下金融数据分析的模式和方法相对复杂。面向大数据样本研究,如何将大样本相比于小样本的独有特征体现在分类模型中值得深入探索。文中从供应链金融数据分布特征入手,分析影响信用风险分类模型的主要因素;对多年来的相关研究成果进行归类分析,概括信用数据分布特征,包括信用数据非均衡与不对称性、信用数据噪声和离群点的存在以及信用数据的非线性多维特征,并探讨了进一步的解决策略。供应链金融大数据分布特征的分析旨在助力挖掘隐含在海量金融数据背后的知识信息,为信用风险模型的构建奠定了坚实的基础。The semi-structured,unstructured and massive supply chain finance data make the analysis method relatively complicated in large data environment.How to use the unique characteristics of large samples to improve classification performance is worth exploring for the research on large data samples.This paper analyzed the main factors,which affect the classification model of credit risk based on the distribution characteristics of financial data in supply chain,proposed distribution characteristics of credit data after researching the relevant achievements over the years,including imbalance data,noise and outliers,nonlinear multidimensional and so on,and then discussed further solutions to mine the know-ledge of the massive financial data,which provides an effective theoretical basis for the construction of credit risk model.

关 键 词：供应链金融 信用风险 大数据 分布特征 非均衡数据 离群点 多维 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]