Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Low rank representation and discriminant analysis-based models for peer-to-peer default risk assessment

Low rank representation and discriminant analysis-based models for peer-to-peer default risk... This study aims to assess the default risk of borrowers in peer-to-peer (P2P) online lending platforms. The authors propose a novel default risk classification model based on data cleaning and feature extraction, which increases risk assessment accuracy.Design/methodology/approachThe authors use borrower data from the Lending Club and propose the risk assessment model based on low-rank representation (LRR) and discriminant analysis. Firstly, the authors use three LRR models to clean the high-dimensional borrower data by removing outliers and noise, and then the authors adopt a discriminant analysis algorithm to reduce the dimension of the cleaned data. In the dimension-reduced feature space, machine learning classifiers including the k-nearest neighbour, support vector machine and artificial neural network are used to assess and classify default risks.FindingsThe results reveal significant noise and redundancy in the borrower data. LRR models can effectively clean such data, particularly the two LRR models with local manifold regularisation. In addition, the supervised discriminant analysis model, termed the local Fisher discriminant analysis model, can extract low-dimensional and discriminative features, which further increases the accuracy of the final risk assessment models.Originality/valueThe originality of this study is that it proposes a novel default risk assessment model, based on data cleaning and feature extraction, for P2P online lending platforms. The proposed approach is innovative and efficient in the P2P online lending field. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Systems and Information Technology Emerald Publishing

Low rank representation and discriminant analysis-based models for peer-to-peer default risk assessment

Download PDF
16 pages

Loading next page...
 
/lp/emerald-publishing/low-rank-representation-and-discriminant-analysis-based-models-for-0EK0SajAkh

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1328-7265
eISSN
1328-7265
DOI
10.1108/jsit-03-2020-0040
Publisher site
See Article on Publisher Site

Abstract

This study aims to assess the default risk of borrowers in peer-to-peer (P2P) online lending platforms. The authors propose a novel default risk classification model based on data cleaning and feature extraction, which increases risk assessment accuracy.Design/methodology/approachThe authors use borrower data from the Lending Club and propose the risk assessment model based on low-rank representation (LRR) and discriminant analysis. Firstly, the authors use three LRR models to clean the high-dimensional borrower data by removing outliers and noise, and then the authors adopt a discriminant analysis algorithm to reduce the dimension of the cleaned data. In the dimension-reduced feature space, machine learning classifiers including the k-nearest neighbour, support vector machine and artificial neural network are used to assess and classify default risks.FindingsThe results reveal significant noise and redundancy in the borrower data. LRR models can effectively clean such data, particularly the two LRR models with local manifold regularisation. In addition, the supervised discriminant analysis model, termed the local Fisher discriminant analysis model, can extract low-dimensional and discriminative features, which further increases the accuracy of the final risk assessment models.Originality/valueThe originality of this study is that it proposes a novel default risk assessment model, based on data cleaning and feature extraction, for P2P online lending platforms. The proposed approach is innovative and efficient in the P2P online lending field.

Journal

Journal of Systems and Information Technology – Emerald Publishing

Published: Apr 11, 2022

Keywords: Feature extraction; Dimension reduction; Data clean; Low-rank representation; P2P online lending

References

  • Improving experimental studies about ensembles of classifiers for bankruptcy prediction and credit scoring
    Abellán, J.; Mantas, C.J.
  • Determinants of default in P2P lending
    Carlos, S.C.; Begona, G.N.; Luz, L.P.
  • Inferences of default risk and borrower characteristics on P2P lending
    Cathy, W.S.; Chen, M.C.D.; Liu, N.; Sriboonchitta, S.
  • Linear dimensionality reduction: survey, insights, and generalizations
    Cunningham, J.P.; Ghahramani, Z.
  • Peer to peer lending: structures, risks and regulation
    Davis, K.T.; Murphy, J.
  • Borrower’s self-disclosure of social media information in P2P lending
    Ge, R.; Gu, B.; Feng, J.
  • Instance-based credit risk assessment for investment decisions in P2P lending
    Guo, Y.; Zhou, W.; Luo, C.; Liu, C.; Xiong, H.
  • Improving credit risk prediction in online peer-to-peer (P2P) lending using feature selection with deep learning
    Ha, V.S.; Lu, D.H.; Choi, G.S.; Nguyen, H.N.; Yoon, B.
  • Trust and credit: the role of appearance in peer-to-peer lending
    Jefferson, D.; Stephan, S.; Lance, Y.
  • Probabilistic non-linear principal component analysis with Gaussian process latent variable models
    Lawrence, N.
  • The mechanism and effectiveness of credit scoring of P2P lending platform: evidence from Renrendai
    Li, Q.; Chen, L.; Zeng, Y.
  • A new aspect on P2P online lending default prediction using Meta-level phone usage data in China
    Ma, L.; Zhao, X.; Zhou, Z.; Liu, Y.
  • Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGBoost algorithms according to different high dimensional data cleaning
    Ma, X.; Sha, J.; Wang, D.; Yu, Y.; Yang, Q.; Niu, Y.
  • Dimensionality reduction: a comparative review
    Maaten, V.D.; Postma, E.O.; Herik, V.D.
  • Laplacian regularized low-rank representation and its applications
    Min, Y.; Gao, J.; Lin, Z.
  • An empirical study on prediction of the default risk on P2P lending platform
    Qian, M.; Hu, F.
  • Dimension reduction of multimodal labeled data by local Fisher discriminant analysis
    Sugiyama, M.
  • Research on influencing factors of P2P network loan prepayment risk based on Cox proportional hazards
    Wan, J.; Zhang, H.; Zhu, X.; Sun, X.; Li, G.
  • A PSO-Based ensemble model for peer-to-Peer credit scoring
    Wang, C.; Hu, Z.; Chiong, R.; Dhakal, S.; Chen, Y.; Bao, Y.
  • Low-rank representation with adaptive graph regularization
    Wen, J.; Fang, X.; Xu, Y.; Tian, C.; Fei, L.
  • Predicting loan default in peer‐to‐peer lending using narrative data
    Xia, Y.; He, L.; Li, Y.; Liu, N.; Ding, Y.
  • Graph embedding and extensions: a general framework for dimension reduction
    Yan, S.; Xu, D.; Zhang, B.; Zhang, H.J.; Yang, Q.; Lin, S.
  • Research on P2P credit risk assessment model based on RBM feature extraction – take SME customers as an example
    Yang, J.; Li, Q.; Luo, D.
  • A data-driven approach to predict default risk of loan for online peer-to-peer (P2P) lending
    Yu, J.; Zhu, Y.
  • Research on credit risk assessment of P2P network platform: based on the logistic regression model of evidence weight
    Zhang, Y.
  • Sparse representation or collaborative representation: which helps face recognition?
    Zhang, L.; Yang, M.; Feng, X.
  • P2P network lending, loss given default and credit risks
    Zhou, G.; Zhang, Y.; Luo, S.
  • Utilities risk indexing – a case for person-to-person (P2P) debit and credit utilities
    Zhou, X.; Qian, W.; Huang, B.; Xu, B.; Su, A.; Cui, W.; Wang, D.; Li, X.; Xu, F.