دانش سرمایه‌گذاری

دانش سرمایه‌گذاری

ارزیابی ریسک اعتباری در وام‌دهی نفر به نفر با استفاده از روش‌های رگرسیون هسته‌ای وزن‌دار شده و رتبه‌بندی ساده

نوع مقاله : مقاله پژوهشی

نویسندگان
هابیل خاوری 1
فاطمه احمدی 2
مجتبی مرادپور 2
رحمت اله محمدی پور 2
رضا مشهدی زاده 3
1 گروه حسابداری و مالی، واحد ایلام، دانشگاه آزاد اسلامی، ایلام، ایران.
2 گروه حسابداری و مالی، واحد ایلام، دانشگاه آزاد اسلامی، ایلام، ایران
3 گروه مدیریت، واحد کرج، دانشگاه آزاد اسلامی، کرج، ایران
10.30495/jik.2023.62005.4296
چکیده
وام‌دهی نفر به نفر روش دیگری از سرمایه‌گذاری است که موجب حذف دخالت موسسات مالی سنتی شده و در سال های اخیر در دیگر کشورها رشد روزافزونی داشته است. هدف این مقاله ارزیابی ریسک اعتباری مبتنی بر نمونه با قابلیت ارزیابی ریسک و بازده هر وام با استفاده از رگرسیون لاجستیک با تابع گوسی که فاقد رویکرد رتبه بندی است در وام دهی نفر به نفر می باشد. برای تایید و اعتبار سنجی تأثیر روش پیشنهادی از پلتفرم وام دهی لندینگ کلاب استفاده شده است. که هر یک از وام گیرندگان دارای مشخصات اعتباری اند. روش اعتبار سنجی k فولد برای تعیین نمونه های اموزشی و تست استفاده شده است. از اینرو با توجه به ده هزار نمونه داده، هفت هزار نمونه وام به تصادف به عنوان نمونه وام آموزش و مابقی سه هزار نمونه وام به عنوان نمونه وام تست در نظر گرفته شده است. نتایج حاصل از آزمایش ها نشان دهنده عملکرد بهتر روش سرمایه گذاری داده محور مبتنی بر رگرسیون هسته‌ای در مقایسه با روش‌های رتبه بندی در کاربرد وام دهی نفر به نفر است.

عنوان مقاله English

Credit risk assessment in person-to-person lending using weighted kernel regression methods and simple ranking

نویسندگان English

Habil Khavari 1
fatemeh ahmadi 2
Mojtaba Moradpour 2
Rahmatollah Mohamadipour 2
Reza Mashhadizadeh 3
1 Accounting and financeDepartment, Ilam Branch, Islamic Azad University, Ilam, Iran
2 Accounting and finance Department, Ilam Branch, Islamic Azad University, Ilam, Iran.
3 Management Department, Karaj Branch, Islamic Azad University, Karaj, Iran
چکیده English

Person-to-person lending is another method of investment that eliminates the involvement of traditional financial institutions and has been growing more and more in recent years in other countries. The purpose of this article is to evaluate the credit risk based on the sample with the ability to evaluate the risk and return of each loan using logistic regression with Gaussian function that does not have a ranking approach in person-to-person lending. Lending Club's lending platform has been used to confirm and validate the effectiveness of the proposed method. that each borrower has a credit profile. The k-fold validation method has been used to determine the training and test samples. Therefore, according to ten thousand data samples, seven thousand random loan samples have been considered as training loan samples and the remaining three thousand loan samples have been considered as test loan samples. The results of the tests show the better performance of the data-driven investment method based on nuclear regression compared to the ranking methods in the application of person-to-person lending.

  1. Club, L., Lending club. 2016, Recuperado el.
  2. de Paula, D.A.V., et al., Estimating credit and profit scoring of a Brazilian credit union with logistic regression and machine-learning techniques. 2019.
  3. Djeundje, V.B. and J.J.E.J.o.O.R. Crook, Dynamic survival models with varying coefficients for credit risks. 2019. 275(1): p. 319-333.
  4. Du, N., et al., Prosocial compliance in P2P lending: A natural field experiment. 2020. 66(1): p. 315-333.
  5. Emekter, R., et al., Evaluating credit risk and loan performance in online Peer-to-Peer (P2P) lending. 2015. 47(1): p. 54-70.
  6. Faradharmastuti, C., &Laurentxius, J. (2021). Factors and benefits that affect lender’s interest in giving loans in peer to peer (P2P) lending platform. Binus Business Review, 12(2), 121-130. https://doi.org/10.21512/bbr.v12i2.6359
  7. Ferreira, V., Papaoikonomou, E., &Terceño, A. (2022). Unpeel the layers of trust! A comparative analysis of crowdfunding platforms and what they do to generate trust. Business Horizons, 65(1), 7-19. https://doi.org/10.1016/j.bushor.2021.08.004.
  8. Guo, Y., et al., Instance-based credit risk assessment for investment decisions in P2P lending. 2016. 249(2): p. 417-426.
  9. Habachi, M., S.J.C.B. Benbachir, and Management, Combination of linear discriminant analysis and expert opinion for the construction of credit rating models: The case of SMEs. 2019. 6(1): p. 1685926.
  10. Harvey, J. (2018). Peer to peer investing guide for beginners. https://www.amazon.com/Peer -Peer -Investing-Guide-Beginnersebook/dp/B079J6JX62/ref.
  11. Jiang, J., Liao, L., Wang, Z., & Zhang, X. (2021). Government affiliation and peer-to-peer lending platforms in China. Journal of Empirical Finance, 62(June), 87-106. https://doi.org/10.1016/j.jempfin.2021.02.004.
  12. Klafft, M. Online peer-to-peer lending: a lenders' perspective. in Proceedings of the international conference on E-learning, E-business, enterprise information systems, and E-government, EEE. 2008.
  13. Larrimore, L., et al., Peer to peer lending: The relationship between language features, trustworthiness, and persuasion success. 2011. 39(1): p. 19-37.
  14. Leonard, T., Logistic Regression, in A Course in Categorical Data Analysis. 2020, Chapman and Hall/CRC. p. 139-152.
  15. Luo, S., Sun, Y., Yang, F., & Zhou, G. (2022). Does fintech innovation promote enterprise transformation? Evidence from China. Technology in Society, 68, 1-13. https://doi.org/10.1016/j.techsoc.2021.101821.
  16. Möstel, L., M. Pfeuffer, and M.J.C.S. Fischer, Statistical inference for Markov chains with applications to credit risk. 2020: p. 1-26.
  17. Mudjahidin, Hidayat, A. A., &Aristio, A. P. (2022). Conceptual model of use behavior for peer-to-peer lending in Indonesia. Procedia Computer Science, 197, 215-222. https://doi.org/10.1016/j.procs.2021.12.134.
  18. Pabst, S., Wayand, M., & Mohnen, A. (2021). Coordinating contributions in crowdfunding for sustainable entrepreneurship. Journal of Cleaner Production, 319, 1-8. https://doi.org/10.1016/j.jclepro.2021.128677.
  19. Puro, L., et al., Borrower decision aid for people-to-people lending. 2010. 49(1): p. 52-60.
  20. Emekter, Y. Tu, B. Jirasakuldech, and M. J. A. E. Lu, "Evaluating credit risk and loan performance in online Peer-to-Peer (P2P) lending," vol. 47, no. 1, pp. 54-70, 2014.
  21. Raboun, O., E. Chojnacki, and A. Tsoukias. Dynamic-R: A New “Convincing” Multiple Criteria Method for Rating Problem Statements. in International Conference on Decision Support System Technology. 2019. Springer.
  22. Safidastjerdi, D., Tayebi, K., &Elahi, N. (2021). Loan interest rate uncertainty and financing SMEs listed in Tehran stock exchange.Journal of Asset Management and Financing, 9(2), 1-20. https://doi.org/10.22108/AMF.2020.124509.1578. (In Persian)
  23. Song, P., Chen, Y., Zhou, Z., & Wu, H. (2018). Performance analysis of peer-to-peer online lending platforms in China, Sustainability,10(9), 1-15. https://doi.org/10.3390/su10092987
  24. Suryono, R. R., Budi, I., & Purwandari, B. (2021). Detection of fintech P2P lending issues in Indonesia. Heliyon, 7(4), 1-10.https://doi.org/10.1016/j.heliyon.2021.e06782
  25. Tao, W. and D. Chang. Credit Risk Assessment of P2P Lending Borrowers based on SVM. in 1st International Conference on Business, Economics, Management Science (BEMS 2019). 2019. Atlantis Press.
  26. Thomas, L., J. Crook, and D. Edelman, Credit scoring and its applications. 2017
  27. Wang, C., Zhang, W., Zhao, X., & Wang, J. (2019). Soft information in online peer-to-peer lending: Evidence from a leading platformin China. Electronic Commerce Research and Applications, 36, 1-15, https://doi.org/10.1016/j.elerap.2019.100873.
  28. Welack, S.J.A.a.S., Artificial Neural Network Approach to Counterparty Credit Risk and XVA. 2019.
  29. Wu, J. and Y.J.J. Xu, A Decision Support System for Borrower's Loan in P2P Lending. 2011. 6(6): p. 1183-1190.
  30. Ye, X., et al., Loan evaluation in P2P lending based on random forest optimized by genetic algorithm with profit score. 2018. 32: p. 23-36.
  31. Yu, S., & Fleming, L. (2021). Regional crowdfunding and high tech entrepreneurship. Research Policy, 1-18.https://doi.org/10.1016/j.respol.2021.104348
  32. Zhang, H., The impact of distance, feature weighting and selection for KNN in credit default prediction. 2020.
  33. Zhao, C., Li, M., Wang, J., & Ma, S. (2021). The mechanism of credit risk contagion among internet P2P lending platforms based on a SEIR model with time-lag. Research in International Business and Finance, 1-10. https://doi.org/10.1016/j.ribaf.2021.101407.