AAM  >> Vol. 5 No. 2 (May 2016)

    基于BP神经网络的P2P个人信用风险仿真模型
    P2P Personal Credit Risk Simulation Model Based on BP Neural Network

  • 全文下载: PDF(2215KB) HTML   XML   PP.192-207   DOI: 10.12677/AAM.2016.52026  
  • 下载量: 527  浏览量: 1,001   科研立项经费支持

作者:  

包丽艳,李淑锦:杭州电子科技大学经济学院,浙江 杭州

关键词:
P2P网贷信用风险BP神经网络P2P Network Loan Credit Risk BP Neural Network

摘要:
近年来我国P2P网络借贷平台处于快速发展阶段,截止2015年8月成交量达到974.63亿元,但平台信用风险已经凸显,持续出现倒闭现象,能否有效识别借款者并控制其信用风险直接影响P2P平台未来的发展。文中介绍了我国P2P网络借贷平台的主要风险,分析了BP神经网络原理及其在P2P个人借款者信用风险评估上的适用性。通过建立P2P个人借款者信用评价体系,搜集人人贷个人借款者信息,运用BP神经网络仿真得到P2P网络借贷个人借款者的信用评级。并在数据缺失情况下进行仿真,与网站评级进行比较可知仿真结果较为准确,能有效评估个人借款者信用风险。在分析的基础上,给出网络平台建议和对策。

In recent years, P2P lending platforms are in a stage of rapid development in our country. By Au-gust 2015, its turnover has reached 97.463 billion Yuan, but the credit risk starts to highlight. There are many platforms that continue to collapse. Whether we can identify and control the credit risk of borrowers effectively directly influences the development of P2P platform in the future. This paper introduces the main risk of P2P network platform in China, and analyzes the basic principles of BP neural network and its application on the applicability of credit risk assessment of individual borrowers. By establishing P2P individual borrower credit evaluation system, and collecting all information from Renrendai, this paper simulates P2P lending individual borrower’s credit rating by BP neural network. And we carry on the simulation under the condition of lack of data; the rating simulation results are more accurate; we can evaluate the credit risk of the individual borrowers effectively. On the basis of the analysis, we propose the suggestions and countermeasures of P2P platform.

文章引用:
包丽艳, 李淑锦. 基于BP神经网络的P2P个人信用风险仿真模型[J]. 应用数学进展, 2016, 5(2): 192-207. http://dx.doi.org/10.12677/AAM.2016.52026

参考文献

[1] 谢平, 邹传伟. 互联网金融模式研究. 金融研究, 2012(12): 11-12.
[2] 宋文, 韩丽川. P2P网络借贷中投资者出借意愿影响因素分析. 西南民族大学学报(自然科学版), 2013(5): 795-799.
[3] 姜岩. P2P网络信贷中借款人的信用风险评估研究[D]: [硕士学位论文]. 南京: 南京理工大学, 2014.
[4] Collier, B.C. and Hampshire, R. (2010) Sending Mixed Signals: Multilevel Reputation Effects in Peer-to-Peer Lending Markets. Proceedings of the 2010 ACM Conference on Computer Supported Cooperative Work, 2, 197-206.
http://dx.doi.org/10.1145/1718918.1718955
[5] 罗洋, 王艳, 许可. 微型金融的新趋势: P2P在线贷款模式. 黑龙江金融, 2009(6): 89-94.
[6] Iyer, R., Khwaja, A.I., Luttmer, E.F. and Shue, K. (2009) Screening in New Credit Markets: Can Individual Lenders Infer Borrower Creditworthiness in Peer-to-Peer Lending? National Bureau of Economic Research No.w15242.
[7] 肖曼君, 欧缘媛, 李颖. 我国P2P网络借贷信用风险影响因素研究——基于排序选择模型的实证分析. 财经理论与实践, 2015(1): 2-6.
[8] Lin, M. (2009) Peer-to-Peer Lending: An Empirical Study. Doctoral Consortium, 12, 147-179.
[9] 王春峰, 万海晖, 张维. 基于神经网络技术的商业银行信用风险评估. 系统工程理论与实践, 1999(9): 24-32.