手机App列表信息在信用风险评价中的应用——基于互联网借贷平台的实证研究

doi:10.16381/j.cnki.issn1003-207x.2021.0359

摘要/Abstract

摘要： 随着互联网的发展和智能手机的普及，用户手机数据被用来评估借款人的信用风险，使用到的数据有通讯记录、短信息接发、移动轨迹、用户行为数据等，而本文研究了手机上所安装的App列表和借款人信用风险之间的关系。通过对某大型互联网借贷平台上的个人借贷数据以及借款人手机上安装的App列表数据的分析发现，手机上安装的App和借款人的信用状况存在关联关系。安装生活类、金融类和买房买车类App的借款人比没有安装这些App的借款人信用风险低；其中，记账类App、外卖类App、股票类App和买房类App对借款人的信用风险有较强的识别能力。把手机App列表信息加入信用风险评价模型之后，信用风险评价模型的区分能力得到显著提高。

关键词: 手机App；信用风险；违约预测；互联网借贷；金融科技

Abstract: With the development of the Internet and popularity of smart phones, data related to the use of mobile devices are used to study the default risk of borrowers, including communication records, short message receiving, mobile track and user behavior data.Data from a large online lending platform are adopted to study whether mobile Apps is related to the credit risk. Three types of Apps are analyzed, namely lifestyle Apps, financial Apps, and property Apps. Personal accounting Apps, takeout Apps and workout Apps are categorized as lifestyle Apps; fund Apps, stock Apps and future Apps are categorized as financial Apps; and car-buying Apps and house-buying Apps are categorized as property Apps. The empirical results show that the usage of these Apps is related to borrowers’ credit risk. Borrowers who install lifestyle Apps, financial Apps, and property Apps have significantly lower credit risk than those who do not install these Apps. In particular, accounting Apps, takeout Apps, stock Apps, and house-buying Apps are good indicators to identify borrowers with good credit.

Key words: mobile App; credit risk; default prediction; online lending; FinTech

中图分类号:

F832.4

郭伟栋, 周志中, 乾春涛. 手机App列表信息在信用风险评价中的应用——基于互联网借贷平台的实证研究[J]. 中国管理科学, 2022, 30(12): 96-107.

GUO Wei-dong, ZHOU Zach Zhi-zhong, QIAN Chun-tao. Application of Mobile App List in Evaluating Borrowers’ Credit Risk——An Empirical Analysis of an Online Lending Platform[J]. Chinese Journal of Management Science, 2022, 30(12): 96-107.

参考文献

［1］中国人民银行征信中心.征信系统建设运行报告(2004-2014)［EB/OL］. (2015-03).http://www.pbccrc.org.cn/zxzx/zxzs/201508/f4e2403544c942cf99d3c71d3b 559236/files/0e78bdbd53cf4ed39b25d886a16054c9.pdf
［2］ Stiglitz J E, Weiss A. Credit rationing in markets with imperfect information［J］. The American Economic Review, 1981, 71(3): 393-410.
［3］ Avery R B, Bostic R W, Samolyk K A. The role of personal wealth in small business finance［J］. Journal of Banking & Finance, 1998, 22: 1019-1061.
［4］李焰, 高弋君, 李珍妮,等. 借款人描述性信息对投资人决策的影响：基于P2P网络借贷平台的分析［J］. 经济研究, 2014(1): 143-155.Li Yan, Gao Yijun, Li Zhenni, et al. The influence of borrower’s description on investors’ decision- Analyze based on P2P online lending［J］. Economic Research Journal, 2014(1): 143-155.
［5］李焰, 张迎新, 王琳.声誉的信息含量——来自P2P网络借贷的证据［J］. 管理评论, 2019, 31: 3-18.Li Yan, Zhang Yingxin, Wang Lin. The information content of reputation- Evidence from peer-peer lending［J］. Management Review, 2019, 31: 3-18.
［6］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.Wang Huijuan, Liao Li. Chinese P2P platform’s credit authentication mechanism research-Evidence from Renrendai［J］. China Industrial Economics, 2014, 4: 136-147.
［7］ Michels J. Do unverifiable disclosures matter? Evidence from peer-to-peer lending［J］. The Accounting Review, 2012, 87(4): 1385-1413.
［8］ Iyer R, Khwaja A L, Luttmer E F P, et al. Screening peers softly: Inferring the quality of small borrowers［J］. Management Science, 2016, 62(6): 1554-1577.
［9］ Seneviratne S, Seneviratne A, Mohapatra P, et al. Predicting user traits from a snapshot of apps installed on a smartphone［J］. ACM SIGMOBILE Mobile Computing and Communications Review, 2014, 18(2): 1-8.
［10］ Xu Runhua, Frey R M, Fleisch E, et al. Understanding the impact of personality traits on mobile app adoption - Insights from a large-scale field study［J］. Computers in Human Behavior, 2016, 62: 244-256.
［11］ Frey R M, Xu Runhua, Ilic A. Mobile app adoption in different life stages: An empirical analysis［J］. Pervasive and Mobile Computing, 2017, 40: 512-527.
［12］ 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.
［13］陈林, 谢彦妩,李平, 等. 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 Yanwu, Li Ping, et al. 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.
［14］王小燕, 张中艳, 马双鸽. 基于文本先验信息的贷款信用风险评估模型［J］. 中国管理科学, 2021, 29(5): 34-44.Wang Xiaoyan, Zhang Zhongyan, Ma Shuangge. A loan credit risk model incorporating text prior information ［J］. Chinese Journal of Management Science, 2021, 29(5): 34-44.
［15］ Lin Mingfeng, Prabhala N R, Viswanathan S. Judging borrowers by the company they keep: Friendship networks and information asymmetry in online peer-to-peer lending［J］. Management Science, 2013, 59(1): 17-35.
［16］ Ge Ruyi, Feng Juan, Gu Bin, et al. Predicting and deterring default with social media information in peer-to-peer lending［J］. Journal of Management Information Systems, 2017, 34(2): 401-424.
［17］ Xu Runhua, Frey R M, Vuckovac D, et al. 2015. Towards understanding the impact of personality traits on mobile app adoption-a scalable approach［C］//Proceedings of 23rd European Conference on Information Systems, Münster, Germany, May 26-29, 2015.
［18］ Lee Y, Park I, Cho S, et al. Smartphone user segmentation based on app usage sequence with neural networks［J］. Telematics and Informatics, 2018, 35: 329-39.
［19］ Frey R， Xu Runhua, Ammendola C,et al. Mobile recommendations based on interest prediction from consumer's installed apps-insights from a large-scale field study［J］. 2017, Information Systems, 71: 152-163.
［20］ Berg T, Burg V, Gombovic＇ A, et al. On the rise of FinTechs: Credit scoring using digital footprints［J］. The Review of Financial Studies, 2020, 33(7): 2845-2897.
［21］ skarsdóttir M, Bravo C, Sarraute C, et al. The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics［J］. Applied Soft Computing, 2019, 74: 26-39.
［22］ Agarwal R R, Lin C C, Chen K T, et al. Predicting financial trouble using call data-On social capital, phone logs, and financial trouble［J］. PLoS One, 2018, 13(2): e0191863.
［23］ Bjrkegren D, Grissen D. Behavior revealed in mobile phone usage predicts credit repayment［J］. The World Bank Economic Review, 2020, 34(3): 618-634.
［24］ Ots H, Liiv I, Tur D. Mobile phone usage data for credit scoring［C］//Proceedings of 14th International Baltic Conference on Databases and Information Systems, Tallinn, Estonia, June 16-19, 2020.
［25］张懿玮, 高维和. 自我建构、文化差异和信用风险——来自互联网金融的经验证据［J］. 财经研究, 2020, 46(1): 34-48.Zhang Yiwei, Gao Weihe. Self-construals, cultural difference and credit risk: evidence from internet finance［J］. Journal of Finance and Economics, 2020, 46(1): 34-48.
［26］ Ma Lin, Zhao Xi, Zhou Zhili, et al. A new aspect on P2P online lending default prediction using meta-level phone usage data in China［J］. Decision Support Systems, 2018, 111: 60-71.
［27］ Lu Tian, Zhang Yingjie, Li Beibei. The value of alternative data in credit risk prediction: Evidence from a large field experiment［C］//Proceedings of Fortieth International Conference on Information Systems, Munich, Germany, December 15-18, 2019.
［28］ Niu Beibei, Ren Jinzhen, Li Xiaotao. Credit scoring using machine learning by combing social network information: Evidence from peer-to-peer lending［J］. Information, 2019, 10(12).
［29］ Shema A. Effective credit scoring using limited mobile phone data［C］//Proceedings of the Tenth International Conference on Information and Communication Technologies and Development,Ahmedabad, India, January 4-7, 2019.
［30］ Roa L, Correa-Bahnsen A, Suarez G, et al. Super-app behavioral patterns in credit risk models: Financial, statistical and regulatory implications［J］. Expert Systems with Applications, 2021, 169.
［31］陈丹.北京市外卖O2O型餐饮业消费者行为特征分析［D］. 兰州: 兰州大学,2019.Chen Dan. Analysis of consumer behavior characteristics of take-out O2O catering industry in Beijing［D］. Lanzhou: Lanzhou University,2019.
［32］廖理, 吉霖, 张伟强.借贷市场能准确识别学历的价值吗?——来自 P2P 平台的经验证据［J］. 金融研究, 2015(3): 146-159.Liao Li, Ji Lin, Zhang Weiqiang. Education and credit: Evidence from P2P lending platform［J］. Journal of Financial Research, 2015(3): 146-159.
［33］徐佳, 谭娅.中国家庭金融资产配置及动态调整［J］. 金融研究, 2016(12): 95-110.Xu Jia, Tan Ya. The dynamic adjustment of Chinese households’ financial asset allocation ［J］. Journal of Financial Research, 2016(12): 95-110.
［34］ Blchlinger A, Leippold M. Economic benefit of powerful credit scoring［J］. Journal of Banking & Finance, 2006, 30(3): 851-873.
［35］ Stein R M. The relationship between default prediction and lending profits: Integrating ROC analysis and loan pricing［J］. Journal of Banking & Finance, 2005, 29(5): 1213-1236.
［36］ Bequé A, Coussement K, Gayler R, et al. Approaches for credit scorecard calibration: An empirical analysis［J］. Knowledge-Based Systems, 2017, 134: 213-227.
［37］ Fernandes G B, Artes R. Spatial dependence in credit risk and its improvement in credit scoring［J］. European Journal of Operational Research, 2016, 249(2): 517-524.

[1]	李冬冬, 李春发, 王晟锴. 行业自律机制下P2P网贷平台违规治理演化博弈[J]. 中国管理科学, 2022, 30(10): 96-108.
[2]	肖和录, 王善平. 基于机会约束随机Index-DEA的投资组合效率评价[J]. 中国管理科学, 2022, 30(9): 94-104.
[3]	安辉, 何萱, 邹千邈. 中国房地产限售政策对房价的影响研究——兼论限售和限购的政策组合效应[J]. 中国管理科学, 2021, 29(8): 35-43.
[4]	李哲, 迟国泰. 基于最大指标区分度与最优相对隶属度的上市公司信用风险研究[J]. 中国管理科学, 2021, 29(4): 1-15.
[5]	王宗润, 陈曦. 心理因素、交易环境变化与结构性产品风险测度:一个研究综述[J]. 中国管理科学, 2020, 28(8): 15-29.
[6]	黄创霞, 温石刚, 杨鑫, 文凤华, 杨晓光. 个体投资者情绪与股票价格行为的互动关系研究[J]. 中国管理科学, 2020, 28(3): 191-200.
[7]	张李登, 唐齐鸣, 张誉航. 房价波动、住房信贷与宏观审慎政策[J]. 中国管理科学, 2019, 27(6): 1-9.
[8]	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.
[9]	赵志冲, 迟国泰. 基于似然比检验的工业小企业债信评级研究[J]. 中国管理科学, 2017, 25(1): 45-56.
[10]	刘渝琳, 郑效晨. 基于通货膨胀和风险偏好视角的资产配置研究[J]. 中国管理科学, 2016, 24(5): 46-53.
[11]	陆静, 周媛. 投资者情绪对股价的影响——基于AH股交叉上市股票的实证分析[J]. 中国管理科学, 2015, 23(11): 21-28.
[12]	尹力博, 韩立岩. 基于多阶段随机规划模型的国债动态积极投资策略[J]. 中国管理科学, 2015, 23(6): 9-16.
[13]	刘婧宇, 夏炎, 林师模, 吴洁, 范英. 基于金融CGE模型的中国绿色信贷政策短中长期影响分析[J]. 中国管理科学, 2015, 23(4): 46-52.
[14]	顾雪松, 韩立岩. 区域市场整合与对外直接投资的逆向溢出效应——来自中国省级行政区的经验证据[J]. 中国管理科学, 2015, 23(3): 1-12.
[15]	李春红, 王苑萍, 郑志丹. 双重委托代理对上市公司过度投资的影响路径分析——基于异质性双边随机边界模型[J]. 中国管理科学, 2014, 22(11): 131-139.