借款陈述文字中的违约信号——基于P2P网络借贷的实证研究

doi:10.16381/j.cnki.issn1003-207x.2019.04.004

中国管理科学 ›› 2019, Vol. 27 ›› Issue (4): 37-47.doi: 10.16381/j.cnki.issn1003-207x.2019.04.004

借款陈述文字中的违约信号——基于P2P网络借贷的实证研究

陈林, 谢彦妩, 李平, 李强

电子科技大学经济与管理学院, 四川成都 611731

收稿日期:2017-04-07 修回日期:2018-05-04 出版日期:2019-04-20 发布日期:2019-06-12
通讯作者: 李平(1977-),男(汉族),四川青神人,电子科技大学经济与管理学院,教授,博士;研究方向:互联网金融、市场微观结构,E-mail:lip@uestc.edu.cn. E-mail:lip@uestc.edu.cn
基金资助:
国家自然科学基金资助项目（71571030）；成都市科技项目（2015-RK00-00063-ZF）；电子科技大学成都研究院产业化研发专项资助项目（RWS-CYHKF-01-20150004）

The Signal of Default Risk from the Description-text Based on the Empirical Research of P2P Lending

CHEN Lin, XIE Yan-wu, LI Ping, LI Qiang

School of Management and Economics, University of Electronic Science and Technology of China, Chengdu 611731, China

Received:2017-04-07 Revised:2018-05-04 Online:2019-04-20 Published:2019-06-12

摘要/Abstract

摘要： P2P借贷让借款人可以通过借款陈述文本去获得投资者的信任，所以借款陈述又成为投资者识别借款人违约风险的重要信息来源。但是如何解读复杂的、不规则的、包含各种信息的借款陈述面临较大挑战。针对违约风险的两个来源：还款能力和还款意愿，以及它们的潜在因素，从P2P借贷平台‘人人贷’借款项目中的借款陈述文本中，通过人工识别提取了文字特征信息、反映还款能力和还款意愿的信息以及对资金需求的情感特征信息，并检验这些信息对识别借款人违约风险的显著性。研究发现借款陈述文本的字数越多、存在重复语句，违约风险越大；借款陈述文本中存在还款能力信息，或者同时存在表示还款意愿的保证性语言以及对自己信用状态补充说明的信息，则违约风险越小；借款人在情感上表现出对资金需求的急切性越高，违约风险越大。研究结论为将来运用程序实现智能文本算法识别借款陈述文本中的违约信息提供了研究方向。

关键词: P2P借贷, 借款陈述, 违约风险, 还款意愿, 情感特征

Abstract: P2P lending let borrowers to obtain trust of investors through a description-text of borrower. So the description-text of borrower is an important information for investors to identify default risk of borrowers. However, how to interpret description-text with the complex, irregular and contain various kinds of information faces great challenges. According to the two factors of default risk:repayment ability and willingness to repay, as well as their potential factors, some text features,information of repayment ability and willingness to repay as well as emotional characteristics of the demand for funds are extracted from description-texts through manual identification, and the significance of those information to identify the default risk of borrowers is tested. It is found that the more words in the description-text, the more repetition sentences existing, and the default risk is greater. There is information of repayment ability or the guarantee language indicating the willingness to repay the loan and the supplementary explanation of the credit status in the description-text, the default risk is smaller. The greater the urgency of the borrower's emotionally expressed need for the loan, the greater the default risk is. The conclusion of the research provides the research direction for the future application of intelligent text algorithm to identify the default information in the description-text related borrowing.

Key words: P2P lending, description-text of borrower, default risk, willingness to repay, emotion characteristics

中图分类号:

F830.589

陈林, 谢彦妩, 李平, 李强. 借款陈述文字中的违约信号——基于P2P网络借贷的实证研究[J]. 中国管理科学, 2019, 27(4): 37-47.

CHEN Lin, XIE Yan-wu, LI Ping, LI Qiang. The Signal of Default Risk from the Description-text Based on the Empirical Research of P2P Lending[J]. Chinese Journal of Management Science, 2019, 27(4): 37-47.

参考文献

[1] 潘彬,杨鑫,肖继宏,等.民间金融与中国宏观经济——理论机制与实证分析[J].中国管理科学,2018,26(3):51-58.

[2] 肖进,薛书田,黄静,等.客户信用评估半监督协同训练模型研究[J].中国管理科学,2016,24(6):124-131.

[3] 王会娟,廖理.中国P2P网络借贷平台信用认证机制研究——来自"人人贷"的经验证据[J]. 中国工业经济,2014,(4):136-147.

[4] Lin M F, Prabhala N R, Viswanathan S. Can Social Networks Help Mitigate Information Asymmetry in Online Markets?[C]//ICIS 2009 Proceedings,Phoenial,Dec 15-18,2009.

[5] 杨立,赵翠翠,陈晓红.基于社交网络的P2P借贷信用风险缓释机制研究[J].中国管理科学,2018,26(1):47-56.

[6] 陈冬宇,朱浩,郑海超.风险、信任和出借意愿-基于拍拍贷注册用户的实证研究[J].管理评论,2014, 26(1):150-158.

[7] Michels J. Do unverifiable disclosures matter? Evidence from peer-to-peer lending[J]. Accounting Review, 2012, 87(4):1385-1413.

[8] Gao Qiang,Lin Mingfeng. Lemon or cherry? The value of texts in debt crowdfunding[R]. Working Paper, SSRN,2015.

[9] Stein J C. Information production and capital allocation:Decentralized versus hierarchical firms[J].The Journal of Finance,2002, 57(5):1891-1921.

[10] 蒋翠清,王睿雅,丁勇.融入软信息的P2P网络借贷违约预测方法[J].中国管理科学,2007,25(11):12-21.

[11] Pennebaker J W, Mehl M R, Niederhoffer K G. Psychological aspects of natural language. use:Our words, our selves[J]. Psychology, 2003, 54(54):547-77.

[12] Martens M L, Jennings P D. Do the stories they tell get them the money they need? The role of entrepreneurial narratives in resource acquisition[J]. Academy of Management Journal, 2007, 50(5):1107-1132.

[13] Chen X P, Yao X, Kotha S. Entrepreneur passion and preparedness in business plan presentations:A persuasion analysis of venture capitalists' funding decisions[J]. Academy of Management Journal, 2009, 52(1):199-214.

[14] 蒋艳辉,马超群,熊希希.创业板上市公司文本惯性披露信息、信息相似度和资产定价-基于French改进模型的经验分析[J].中国管理科学,2014,22(8):56-63.

[15] Larrimore L, Jiang L, Larrimore J, et al. Peer to peer lending:The relationship between language features, trustworthiness, and persuasion success[J]. Journal of Applied Communication Research, 2011, 39(1):19-37.

[16] Herzenstein M, Sonenshein S, Dholakia U M. Tell me a good story and I may lend you money:The role of narratives in peer-to-peer lending decisions[J]. Journal of Marketing Research, 2011, 48(SPL):138-149.

[17] 廖理,吉霖,张伟强. 语言可信吗?借贷市场上语言的作用——来自P2P平台的证据[J]. 清华大学学报(自然科学版),2015,55(4):413-421.

[18] Pope D G, Sydnor J R. What's in a picture?:Evidence of discrimination from prosper.com[J]. Journal of Human Resources, 2011, 46(1):53-92.

[19] Duarte J, Siegel S, Young L. Trust and credit:The role of appearance in peer-to-peer lending[J]. Review of Financial Studies, 2012, 25(8):2455-2484.

[20] Newman M L,Pennebaker J W, Berry D S,et al. Lying words:Predicting deception from linguistic styles[J].Personality and Social Psychology Bulletin, 2003, 29(5):665-675.

[21] 魏韡,向阳,陈千.中文文本情感分析综述[J].计算机应用,2011,31(11):3321-3323.

[22] 燕飞.中文文本情感分析研究综述[J].计算机应用研究,2012,29(6):2014-2017.

[23] Kennedy P. A Guide to Econometrics(6th Edition)[M].Blackwell,2008.

借款陈述文字中的违约信号——基于P2P网络借贷的实证研究

The Signal of Default Risk from the Description-text Based on the Empirical Research of P2P Lending

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

Metrics

本文评价

推荐阅读 10

[1]	钱雪松, 屈伸, 康瑾, 杜立. 中国影子银行违约风险和防范机制研究——来自上市公司委托贷款数据的经验证据[J]. 中国管理科学, 2020, 28(7): 35-44.
[2]	冯玲, 文璐, 肖阳. 基于政府隐性担保退出预期的金融机构违约风险重定价[J]. 中国管理科学, 2020, 28(11): 43-50.
[3]	黄苒, 范群, 郭峰. 中小企业违约风险系统性和异质性测度——基于违约风险成分分析法的研究[J]. 中国管理科学, 2018, 26(3): 13-21.
[4]	廖理, 向佳, 王正位. P2P借贷投资者的群体智慧[J]. 中国管理科学, 2018, 26(10): 30-40.
[5]	杨立, 赵翠翠, 陈晓红. 基于社交网络的P2P借贷信用风险缓释机制研究[J]. 中国管理科学, 2018, 26(1): 47-56.
[6]	蒋翠清, 王睿雅, 丁勇. 融入软信息的P2P网络借贷违约预测方法[J]. 中国管理科学, 2017, 25(11): 12-21.
[7]	彭红枫, 叶永刚. 基于还款能力和还款意愿的贷款定价模型研究[J]. 中国管理科学, 2011, 19(6): 40-47.
[8]	彭红枫, 叶永刚. 基于资本监管要求和还款意愿的贷款定价研究[J]. 中国管理科学, 2009, 17(2): 8-14.