International Journal of Applied Science and Engineering

Published by Chaoyang University of Technology

Shin-Fu Chena, Goutam Charkabortyb, Li-Hua Lia* and Chi-Tien Linc

aInformation Management Department, Chaoyang University of Technology Taichung, Taiwan
bSoftware and Information Science Department, Iwate Prefectural University, Iwate, Japan
cFinancial Engineering Department, Providence University, Taichung, Taiwan


Download Citation: |
Download PDF


The financial market crashed after Lehman Shock in 2008 which creates the risk averting environment for banks. Under this kind of environment, it has become difficult for new and small businesses to have access to loans. Since then, P2P (Peer to Peer) lending becomes more and more popular around the world. However, most of the researches who had studied about credit risk on P2P lending consider only the event that the borrower will default instead of the amount of loss. In this work, we consider Net Return Rate (NRR) as the criterion to label the data for prediction training. We train the regression model to assess credit risk. The proposed model predicts the amount of profit from a borrower. In our results, by using our proposed credit risk assessment model, an investor of P2P lending can measure the risk with better accuracy and the proposed model can also predict the amount of profit from a loan.

Keywords: P2P lending; random forest; logistic regression; credit risk; credit scoring.

Share this article with your colleagues



  1. [1] Working Group of CGFS and FSB. 2017. FinTech Credit: Market Structure, Business Models and Financial Stability Implications, Report. Bank for International Settlements and Financial Stability Board,, ISBN 978-92-9259-051-2 online.

  2. [2] Malekipirbazari, Milad & Aksakalli, V. 2015. Risk assessment in social lending via random forests. Expert Systems with Applications, 40, 10 : 4621-4631.

  3. [3] Thomas, L. C. 2000. A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers. International journal of forecasting, 16, 2 : 149-172.

  4. [4] Emekter, R., Tu, Y., Jirasakuldech, B., & Lu, M. 2015. Evaluating credit risk and loan performance in online Peer-to-Peer (P2P) lending. Applied Economics, 47, 1 : 54-70.

  5. [5] Carlos Serrano-Cinca & BegoñaGutiérrez-Nieto, 2016, “The use of profit scoring as an alternative to credit scoring systems in peer-to-peer (P2P) lending,” Decision Support Systems, vol. 89, pp. 113-122.

  6. [6] Serrano-Cinca, C. and Gutiérrez-Nieto, B. 2016. The use of profit scoring as an alternative to credit scoring systems in peer-to-peer (P2P) lending. Decision Support Systems,
    89 : 113-122

  7. [7] Galindo, J. and Tamayo, P. 2000. Credit risk assessment using statistical and machine learning: basic methodology and risk modeling applications. Computational Economics, 15, 1-2 : 107-143.

  8. [8] Wiginton, J. 1980. A Note on the Comparison of Logit and Discriminant Models of Consumer Credit Behavior. Journal of Financial and Quantitative Analysis, 15, 3 : 757-770

  9. [9] Breiman, L. 2001. Random forests. Machine learning, 45, 1 : 5-32.

  10. [10] Barandiaran, I. 1998. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 8.

  11. [11] Segal, M. R. 2004. Machine learning benchmarks and random forest regression. Technical Report, Center for Bioinformatics & Molecular Biostatistics, University of California,

  12. [12] Open Data of Lending Club, Available at:, extracted at Sep.


Received: 2019-05-28
Revised: 2019-09-23
Accepted: 2019-09-30
Publication Date: 2019-09-01

Cite this article:

Chen, S.F., Charkaborty, G., Li, L.H., Lin, C.T. 2019. Credit risk assessment using regression model on P2P lending. International Journal of Applied Science and Engineering, 16, 149-157.

We use cookies on this website to improve your user experience. By using this site you agree to its use of cookies.