Abstract
The ever increasing development of P2P lending accumulates tremendous transaction data, a central question on these platforms is how to align the right products with the right investors. Most of the existing methods adapt some well-studied strategies for recommendation, we argue that an inherent drawback of such methods is that, the unique characteristics in the P2P lending scenario, such as the profile of investor, is not fully investigated. As such, the resultant recommendation may easily lead to suboptimal performance.
In this work, we propose to integrate the investor’s profile into the recommendation process. We develop a new recommendation framework enhanced Hybrid graph Ranking using Investor Profile (HRIP), which exploits a hybrid random walk-based recommendation via investor’s profile from both the social and psychology aspects. This leads to the expressive modeling of representation of investor in investor-product hybrid graph, which can effectively deal with cold start users. Comprehensive analysis verifies the importance of the representation of investor, justifying the rationality and effectiveness of HRIP.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
LendingClub: 2019. LendingClub Marketplace. https://www.lendingclub.com/info/statistics.action. Accessed 6 April 2020
Wang, G., et al.: Product supply optimization for crowdfunding campaigns. IEEE Trans. Big Data, 1–1 (2018)
Ma, H., et al.: Matrix factorization recommendation algorithm fusing reliability and influence propagation. ACTA Autom. Sinica (2020)
Zhao, H., et al.: Investment recommendation in P2P lending: a portfolio perspective with risk management. In: 2014 IEEE International Conference on Data Mining, pp. 1109–1114. IEEE (2014)
He, X., et al.: Trirank: review-aware explainable recommendation by modeling aspects. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 1661–1670. ACM (2015)
Eksombatchai, C., et al.: Pixie: a system for recommending 3+ billion items to 200+ million users in real-time. In: Proceedings of the 2018 World Wide Web Conference. International World Wide Web Conferences Steering Committee, pp. 1775–1784 (2018)
Nikolakopoulos, A.N., Karypis, G.: Recwalk: nearly uncoupled random walks for top-n recommendation. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp. 150–158. ACM (2019)
Zhao, H., et al.: Portfolio selections in P2P lending: a multi-objective perspective. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2075–2084. ACM (2016)
Zhang, H., et al.: Finding potential lenders in P2P lending: a hybrid random walk approach. Inf. Sci. 432, 376–391 (2018)
Ceyhan, S., Shi, X., Leskovec, J.: Dynamics of bidding in a P2P lending service: effects of herding and predicting loan success. In: Proceedings of the 20th International Conference on World Wide Web. pp. 547–556. ACM (2011)
Shyng, J.Y., Shieh, H.M., Tzeng, G.H., Tzeng, S.H.: An integration method combining rough set theory with formal concept analysis for personal investment portfolios. Knowl.-Based Syst. 23(6), 586–597 (2010)
Gonzalez-Carrasco, I., Colomo-Palacios, R., Lopez-Cuadrado, J.L., et al.: PB-ADVISOR: a private banking multi-investment portfolio advisor. Inf. Sci. 206, 63–82 (2012)
Powers, D.M.: Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. J. Mach. Learn. Technol. 1(2), 37–63 (2011)
Ricci, Francesco, Rokach, Lior, Shapira, Bracha: Introduction to recommender systems handbook. In: Ricci, Francesco, Rokach, Lior, Shapira, Bracha, Kantor, Paul B. (eds.) Recommender Systems Handbook, pp. 1–35. Springer, Boston, MA (2011). https://doi.org/10.1007/978-0-387-85820-3_1
Acknowledgment
This work is supported by the National Natural Science Foundation of China (61762078, 61363058, 61966004), Research Fund of Guangxi Key Lab of Multi-source Information Mining and Security (MIMS18-08), Major Project of Young Teachers’ Scientific Research Ability Promotion Plan (NWNU-LKQN2019-2), Research Fund of Guangxi Key Laboratory of Trusted Software (kx202003) and Graduate Research Fund Project of Northwest Normal University (2019KYZZ012073).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Y., Ma, H., Jiang, Y., Li, Z. (2020). Top-N Recommendation in P2P Lending: A Hybrid Graph Ranking Using Investor Profile. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12533. Springer, Cham. https://doi.org/10.1007/978-3-030-63833-7_59
Download citation
DOI: https://doi.org/10.1007/978-3-030-63833-7_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63832-0
Online ISBN: 978-3-030-63833-7
eBook Packages: Computer ScienceComputer Science (R0)