Please wait a minute...
Advanced Search
数据分析与知识发现  2019, Vol. 3 Issue (12): 76-83    DOI: 10.11925/infotech.2096-3467.2019.0357
     研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于二部图的P2P网络借贷投资组合决策方法 *
丁勇1,2,程璐1(),蒋翠清1,2
1 合肥工业大学管理学院 合肥 230009
2 过程优化与智能决策教育部重点实验室 合肥 230009
Choosing Portfolios Based on Bipartite Graph of P2P Lending Networks
Yong Ding1,2,Lu Cheng1(),Cuiqing Jiang1,2
1 School of Management, Hefei University of Technology, Hefei 230009, China
2 Key Laboratory of Process Optimization and Intelligent Decision-making of Ministry of Education, Hefei 230009, China
全文: PDF(551 KB)   HTML ( 4
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】基于网贷数据, 通过推荐算法和投资组合理论, 帮助投资者选择投资产品、确定投资金额, 从而提高投资者的满意度和收益率。【方法】基于人人贷交易数据, 通过构建P2P场景下的二部图关系网络图, 利用基于二部图的推荐算法和马科维茨投资组合理论为投资者确定投资产品和投资比例。【结果】实验结果表明, 在不同的k值(5、15、25、35、45、50)下, 简单权值改进的二部图推荐算法PNBI的准确率(0.055、0.044、0.039、0.035、0.036、0.032)均高于基于用户的协同过滤算法UCF(0.022、0.019、0.032、0.032、0.033、0.034)和基于物品的协同过滤算法ICF(0.007、0.013、0.014、0.014、0.014、0.014)。PNBI召回率同样高于其他两种算法。【局限】实验数据集有待进一步扩充。【结论】将推荐算法和组合理论相结合, 可以显著提高投资者的满意度以及投资者最终的实际回报率。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
丁勇
程璐
蒋翠清
关键词 P2P网络借贷二部图推荐算法投资组合决策方法    
Abstract

[Objective] This paper proposes a method based on recommendation algorithm, portfolio theory and the actual data of China’s online lending market, aiming to help investors make better decisions. [Methods] We collected data from Renren’s Loan Transaction and constructed a bipartite graph network graph for the P2P scenario. Then, we used the recommendation algorithm and Markowitz portfolio theory to choose the investment products. [Results] Under different K values, the accuracy of the improved bipartite graph recommendation algorithm with simple weight were 0.055, 0.044, 0.039, 0.035, 0.036 and 0.032. These results were higher than those of the user-based collaborative filtering algorithms UCF (0.022, 0.019, 0.032, 0.032, 0.033, 0.034) and item-based collaborative filtering algorithms ICF (0.007, 0.013, 0.014, 0.014, 0.014, 0.014). The recall rate was also higher than those of the other two algorithms. [Limitations] The sample dataset needs to be expanded. [Conclusions] Combining recommendation algorithm with group theory could find portfolios with better return of investments.

Key wordsP2P Network Lending    Bipartite Graph    Recommendation Algorithm    Investment Portfolio    Decision Method
收稿日期: 2019-04-03     
中图分类号:  TP391  
基金资助:*本文系教育部人文社会科学规划基金项目“社会化媒体对企业绩效的影响机制研究”(项目编号: 15YJA630010);国家自然科学基金重点项目“大数据环境下的微观信用评价理论与方法研究”(项目编号: 71731005)
通讯作者: 程璐     E-mail: chengluhs@163.com
引用本文:   
丁勇,程璐,蒋翠清. 基于二部图的P2P网络借贷投资组合决策方法 *[J]. 数据分析与知识发现, 2019, 3(12): 76-83.
Yong Ding,Lu Cheng,Cuiqing Jiang. Choosing Portfolios Based on Bipartite Graph of P2P Lending Networks. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.2096-3467.2019.0357.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2019.0357
图1  借款者和投资者的关系网络
图2  资源分配过程
投资者 v1 v2 v3 v4 v5 v6 v7 v8 v9 v10
1 15 309 11 737 17 135 16 944 15 181 14 584 11 633 19 976 12 988 14 349
2 11 988 12 097 18 336 9 429 9 387 11 780 7 095 12 056 12 988 11 575
3 13 640 13 073 13 084 14 352 14 062 12 988 19 102 19 976 13 681 13 946
4 15 919 11 737 15 112 18 901 11 633 15 579 19 976 16 944 20 084 11 735
5 15 919 17 973 17 065 15 563 19 172 16 944 16 149 18 296 19 976 19 085
表1  K=10时推荐清单
投资者 w1 w2 w3 w4 w5 w6 w7 w8 w9 w10 Ri Ei
1 1.38% 11.19% 1.46% 1.29% 0.03% 5.01% 64.45% 2.13% 12.01% 1.05% 0.54% 15.00%
2 4.18% 6.67% 28.27% 1.04% 6.43% 0.16% 0.07% 32.16% 11.46% 9.56% 0.52% 12.27%
3 3.09% 6.37% 4.12% 0.02% 72.47% 10.13% 0.72% 1.80% 1.02% 0.27% 0.49% 9.88%
4 0.68% 12.63% 0.00% 2.23% 72.80% 0.06% 2.41% 1.46% 2.44% 5.28% 0.57% 14.62%
5 0.67% 1.76% 1.51% 5.47% 10.41% 1.42% 73.77% 0.01% 2.35% 2.63% 0.56% 12.31%
表2  K=10时投资比重
K
算法
5 15 25 35 45 50
PNBI 0.055 0.044 0.039 0.035 0.036 0.032
UCF 0.022 0.019 0.032 0.032 0.033 0.034
ICF 0.007 0.013 0.014 0.014 0.014 0.014
表3  不同K值下准确率比较
K
算法
5 15 25 35 45 50
PNBI 0.032 0.077 0.113 0.143 0.167 0.170
UCF 0.053 0.072 0.079 0.079 0.081 0.083
ICF 0.016 0.032 0.034 0.034 0.034 0.034
表4  不同K值下召回率比较
K
算法
5 10 20 30 40 50
PNBI 0.139 0.136 0.134 0.133 0.132 0.132
UCF 0.138 0.133 0.128 0.129 0.131 0.129
ICF 0.137 0.134 0.132 0.13 0.128 0.125
无推荐 0.114 0.114 0.114 0.114 0.114 0.114
表5  不同K值下实际回报率比较
K 5 10 20 30 40 50
PNBI 9.929 8.726 6.253 5.576 4.738 4.092
UCF 9.125 8.247 7.125 5.236 4.978 3.968
ICF 7.719 4.125 3.283 3.015 2.863 1.238
表6  不同K值下夏普比率比较
[1] 彭倩, 秦进 . P2P网络借贷中历史投资经验对投资人决策的影响[J]. 金融论坛, 2018(5):24-39.
( Peng Qian, Qin Jin . The Impact of Historical Investment Experience on Investor’s Decision in P2P Network Leading[J]. Finance Forum, 2018(5):24-39.)
[2] Namvar A, Siami M, Rabhi F , et al. Credit Risk Prediction in an Imbalanced Social Lending Environment[OL]. arXiv Preprint, arXiv: 1805.00801.
[3] Luo N, Shen F . Investment Pattern Clustering Based on Online P2P Lending Platform [C]// Proceedings of the 15th International Conference on Computer & Information Science. IEEE, 2016.
[4] Stein J C . Information Production and Capital Allocation: Decentralized Versus Hierarchical Firms[J]. The Journal of Financce, 2002,57(5):1891-1921.
[5] 操玮, 李灿, 贺婷婷 , 等. 基于集成学习的中国P2P网络借贷信用风险预警模型的对比研究[J]. 数据分析与知识发现, 2018,2(10):65-76.
( Cao Wei, Li Can, He Tingting , et al. Predicting Credit Risks of P2P Loans in China Based on Ensemble Learning Methods[J]. Data Analysis and Knowledge Discovery, 2018,2(10):65-76.)
[6] 石澄贤, 陈雪交 . P2P网贷个人信用评价指标体系的构建[J]. 常州大学学报: 社会科学版, 2016,17(1):80-85.
( Shi Chengxian, Chen Xuejiao . The Construction of P2P Network Lending Personal Credit Evaluation Index System[J]. Journal of Changzhou University: Social Science Edition, 2016,17(1):80-85.)
[7] 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.
( Jiang Cuiqing, Wang Ruiya, Ding Yong . The Default Prediction Combined with Soft Information Online Peer-to-Peer Lending[J]. Chinese Journal of Management Science, 2017,25(11):12-21.)
[8] 王会娟, 何琳 . 借款描述对P2P网络借贷行为影响的实证研究[J]. 金融经济学研究, 2015,30(1):77-85.
( Wang Huijuan, He Lin . An Empirical Study of Borrowing Description’s Influence on P2P Lending[J]. Journal of Finance and Econcmics, 2015,30(1):77-85.)
[9] Guo Y, Zhou W, Luo C , et al. Instance-based Credit Risk Assessment for Investment Decision in P2P Lending[J]. European Journal of Operational Research, 2015,249(2):417-426.
[10] 张卫国, 卢媛媛, 刘勇军 . 基于非均衡模糊近似支持向量机的P2P网贷借款人信用风险评估及应用[J]. 系统工程理论与实践, 2018,38(10):2466-2478.
( Zhang Weiguo, Lu Yuanyuan, Liu Yongjun . The Borrower’s Credit Risk Assessment in P2P Platform Based on Fuzzy Proximal Support Vector Machine and Its Application[J]. Systems Engineering——Theory & Practice, 2018,38(10):2466-2478.)
[11] 肖会敏, 侯宇, 崔春生 . 基于BP神经网络的P2P网贷借款人信用评估[J]. 运筹与管理, 2018,27(9):112-118.
( Xiao Huimin, Hou Yu, Cui Chunsheng . Evaluation of P2P Lending Borrower’s Credit on BP Artificial Neural Network[J]. Operations Research and Management Science, 2018,27(9):112-118.)
[12] Byanjankar A, Heikkilä M Z, Mezei J . Predicting Credit Risk in Peer-to-Peer Lending: A Neural Network Approach [C] // Proceedings of the 15th IEEE Symposium Series on computational Intelligence. IEEE Computer Society, 2015: 719-725.
[13] 李斌, 谢丰, 陈钟 . 一种面向业务的风险评估模型[J]. 计算机研究与发展, 2011,46(9):1634-1642.
( Li Bin, Xie Feng, Chen Zhong . A Business Oriented Risk Assessment Model[J]. Journal of Computer Research and Development, 2011,46(9):1634-1642.)
[14] Zhao H, Wu L, Liu Q , et al. Investment Recommendation in P2P Lending: A Portfolio Perspective with Risk Management [C]// Proceedings of the 15th IEEE International Conference on Data Mining. IEEE, 2015.
[15] 郭艳红, 刘苇, 雒春雨 . 在线网络借贷投资决策模型及实证研究[J]. 运筹与管理, 2016,25(2):214-219.
( Guo Yanhong, Liu Wei, Luo Chunyu . An Investment Decision Model and Its Experimental Research on P2P Lending Network[J]. Operations Research and Management Science, 2016,25(2):214-219.)
[16] 王茜, 段双艳 . 一种改进的基于二部图网络结构的推荐算法[J]. 计算机研究应用发展, 2013,30(3):771-774.
( Wang Qian, Duan Shuangyan . Improved Recommendation Algorithm Based on Weighted Bipartite Networks[J]. Applications Research of Computers, 2013,30(3):771-774.)
[17] 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.
( Yang Li, Zhao Cuicui, Chen Xiaohong . Research on Credit Risk Mitigation of Peer-to-Peer Lending Based on Social Network[J]. Chinese Journal of Management Science, 2018,26(1):47-56.)
[18] 李玲, 李晋宏 . 基于随机森林修正的加权二部图推荐算法[J]. 软件, 2018,39(1):110-115.
( Li Ling, Li Jinhong . Weighted Bipartite Network Recommendation Based in Random Forest[J]. Computer Engineering & Software, 2018,39(1):110-115.)
[19] 高长元, 段文彬, 张树臣 . 基于差异路径权重的二部图网络推荐算法[J]. 计算机应用研究, 2018,36(3):1-6.
( Gao Changyuan, Duan Wenbin, Zhang Shuchen . Recommendation Algorithm for Bipartite Graph Network Structure Based on Differential Path Weight[J]. Application Research of Computers, 2018,36(3):1-6.)
[20] 万常选, 游运, 江腾蛟 , 等. 考虑投资者朋友关系和预期效用的P2P借贷个性化投资推荐方法[J]. 计算机研究与发展, 2018,55(10):2307-2320.
( Wan Changxuan, You Yun, Jiang Tengjiao , et al. Personalized Investment Recommendation in P2P Lending Considering Friend Relationships and Expected Utilities of Investors[J]. Journal of Computer Research and Development, 2018,55(10):2307-2320.)
[21] 余华银, 雷雅慧 . 基于决策树与Logistic回归的P2P网贷平台信用风险评价比较分析[J]. 长春大学学报, 2017,27(9):13-16.
( Yu Huayin, Lei Yahui . Comparative Analysis on Credict Risk Evaluation of P2P Network Loan Platform Based on Decision Tree and Logistic Regression[J]. Journal of Changchun University, 2017,27(9):13-16.)
[22] Zhang Z, Gao G, Shi Y . Credit Risk Evaluation Using Multi-Criteria Optimization Classifier with Kernel, Fuzzification and Penalty Factors[J]. European Journal of Operational Research, 2014,237(1):335-348.
[23] Tan Y, Zheng X, Zhu M , et al. Investment Recommendation with Total Capital Value Maximization in Online P2P Lending [C]// Proceedings of the 14th International Conference on e-Business Engineering (ICEBE). IEEE, 2017.
[24] Zhou T, Ren J, Medo M , et al. Bipartite Network Projection and Personal Recommendation[J]. Physical Review E, Statistical Nonlinear & Soft Matter Physics, 2007,76(4):046115.
[25] Markowitz H M . Portfolio Selection[J]. Journal of Finance, 1952,1(7):77-91.
[26] 周雅慧, 张一舟, 米晋宏 . IDEA: 一种基于P2P借贷网络的投资决策分析算法[J]. 计算机系统应用, 2016,25(9):200-206.
( Zhou Yahui, Zhang Yizhou, Mi Jinhong . IDEA: An Investment Decision Analysis Algorithm for P2P Lending[J]. Computer Systems &Applications, 2016,25(9):200-206.)
[27] 李汉东, 张吟, 张瑞 . 基于联合违约概率的资产组合投资优化方法[J]. 系统工程理论与实践, 2018,38(3):556-564.
( Li Handong, Zhang Yin, Zhang Rui . The Portfolio Optimization Method Based on Joint Probability of Default[J]. System Engineering-Theory & Practice, 2018,38(3):556-564.)
[28] 项亮 . 推荐系统实战[M]. 第1版. 北京: 人民邮电出版社, 2012.
( Xiang Liang . Recommendation System Practice[M]. The 1st Edition. Beijing: People’s Posts and Telecommunications Publishing House, 2012.)
[29] Sharp W . Mutual Fund Performance[J]. Journal of Business, 1996,39(1):119-138.
[30] Zhao H, Liu Q, Wang G , et al. Portfolio Selection in P2P Lending: A Multi-objective Perspective [C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 2075-2084.
[31] Breese J S, Heckerman D, Kadie C . Empirical Analysis of Predictive Algorithms for Collaborative Filtering [C]// Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers, 2013: 43-52.
[1] 侯君,刘魁,李千目. 基于ESSVM的分类推荐*[J]. 数据分析与知识发现, 2018, 2(3): 9-21.
[2] 操玮,李灿,贺婷婷,朱卫东. 基于集成学习的中国P2P网络借贷信用风险预警模型的对比研究*[J]. 数据分析与知识发现, 2018, 2(10): 65-76.
[3] 王永,邓江洲,邓永恒,张璞. 基于项目概率分布的协同过滤推荐算法*[J]. 现代图书情报技术, 2016, 32(6): 73-79.
[4] 王伟军, 宋梅青. 一种面向用户偏好定向挖掘的协同过滤个性化推荐算法[J]. 现代图书情报技术, 2014, 30(6): 25-32.
[5] 原福永, 蔡红蕾. 一种在信任网络中随机游走的推荐算法[J]. 现代图书情报技术, 2014, 30(10): 70-75.
[6] 任辉,周晓光,申晋 . 基于二部图法的Web知识社群挖掘*[J]. 现代图书情报技术, 2007, 2(4): 39-42.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn