IDEAS home Printed from https://ideas.repec.org/p/hal/cesptp/halshs-01719983.html
   My bibliography  Save this paper

Credit Risk Analysis using Machine and Deep Learning models

Author

Listed:
  • Peter Martey Addo

    (Lead Data Scientist - SNCF Mobilité)

  • Dominique Guegan

    (UP1 - Université Paris 1 Panthéon-Sorbonne, Labex ReFi - UP1 - Université Paris 1 Panthéon-Sorbonne, University of Ca’ Foscari [Venice, Italy], CES - Centre d'économie de la Sorbonne - UP1 - Université Paris 1 Panthéon-Sorbonne - CNRS - Centre National de la Recherche Scientifique, IPAG Business School)

  • Bertrand Hassani

    (Labex ReFi - UP1 - Université Paris 1 Panthéon-Sorbonne, Capgemini Consulting [Paris])

Abstract

Due to the hyper technology associated to Big Data, data availability and computing power, most banks or lending financial institutions are renewing their business models. Credit risk predictions, monitoring, model reliability and effective loan processing are key to decision making and transparency. In this work, we build binary classifiers based on machine and deep learning models on real data in predicting loan default probability. The top 10 important features from these models are selected and then used in the modelling process to test the stability of binary classifiers by comparing performance on separate data. We observe that tree-based models are more stable than models based on multilayer artificial neural networks. This opens several questions relative to the intensive used of deep learning systems in the enterprises.

Suggested Citation

  • Peter Martey Addo & Dominique Guegan & Bertrand Hassani, 2018. "Credit Risk Analysis using Machine and Deep Learning models," Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) halshs-01719983, HAL.
    • Handle: RePEc:hal:cesptp:halshs-01719983
    Note: View the original document on HAL open archive server: https://shs.hal.science/halshs-01719983
    as

    Download full text from publisher

    File URL: https://shs.hal.science/halshs-01719983/document
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Gastwirth, Joseph L, 1972. "The Estimation of the Lorenz Curve and Gini Index," The Review of Economics and Statistics, MIT Press, vol. 54(3), pages 306-316, August.
    2. Lerman, Robert I. & Yitzhaki, Shlomo, 1984. "A note on the calculation and interpretation of the Gini index," Economics Letters, Elsevier, vol. 15(3-4), pages 363-368.
    3. Fan J. & Li R., 2001. "Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties," Journal of the American Statistical Association, American Statistical Association, vol. 96, pages 1348-1360, December.
    4. Yitzhaki, Shlomo, 1983. "On an Extension of the Gini Inequality Index," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 24(3), pages 617-628, October.
    5. Friedman, Jerome H. & Hastie, Trevor & Tibshirani, Rob, 2010. "Regularization Paths for Generalized Linear Models via Coordinate Descent," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 33(i01).
    6. Hui Zou & Trevor Hastie, 2005. "Addendum: Regularization and variable selection via the elastic net," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 67(5), pages 768-768, November.
    7. Hui Zou & Trevor Hastie, 2005. "Regularization and variable selection via the elastic net," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 67(2), pages 301-320, April.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Peter Martey Addo & Dominique Guegan & Bertrand Hassani, 2018. "Credit Risk Analysis using Machine and Deep Learning models," Post-Print halshs-01719983, HAL.
    2. Peter Martey Addo & Dominique Guegan & Bertrand Hassani, 2018. "Credit Risk Analysis Using Machine and Deep Learning Models," Risks, MDPI, vol. 6(2), pages 1-20, April.
    3. Peter Martey Addo & Dominique Guégan & Bertrand Hassani, 2018. "Credit Risk Analysis using Machine and Deep learning models," Documents de travail du Centre d'Economie de la Sorbonne 18003, Université Panthéon-Sorbonne (Paris 1), Centre d'Economie de la Sorbonne.
    4. Tutz, Gerhard & Pößnecker, Wolfgang & Uhlmann, Lorenz, 2015. "Variable selection in general multinomial logit models," Computational Statistics & Data Analysis, Elsevier, vol. 82(C), pages 207-222.
    5. Zichen Zhang & Ye Eun Bae & Jonathan R. Bradley & Lang Wu & Chong Wu, 2022. "SUMMIT: An integrative approach for better transcriptomic data imputation improves causal gene identification," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    6. Peter Bühlmann & Jacopo Mandozzi, 2014. "High-dimensional variable screening and bias in subsequent inference, with an empirical comparison," Computational Statistics, Springer, vol. 29(3), pages 407-430, June.
    7. Capanu, Marinela & Giurcanu, Mihai & Begg, Colin B. & Gönen, Mithat, 2023. "Subsampling based variable selection for generalized linear models," Computational Statistics & Data Analysis, Elsevier, vol. 184(C).
    8. Loann David Denis Desboulets, 2018. "A Review on Variable Selection in Regression Analysis," Econometrics, MDPI, vol. 6(4), pages 1-27, November.
    9. Zeyu Bian & Erica E. M. Moodie & Susan M. Shortreed & Sahir Bhatnagar, 2023. "Variable selection in regression‐based estimation of dynamic treatment regimes," Biometrics, The International Biometric Society, vol. 79(2), pages 988-999, June.
    10. Zanhua Yin, 2020. "Variable selection for sparse logistic regression," Metrika: International Journal for Theoretical and Applied Statistics, Springer, vol. 83(7), pages 821-836, October.
    11. Dumitrescu, Elena & Hué, Sullivan & Hurlin, Christophe & Tokpavi, Sessi, 2022. "Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects," European Journal of Operational Research, Elsevier, vol. 297(3), pages 1178-1192.
    12. Pei Wang & Shunjie Chen & Sijia Yang, 2022. "Recent Advances on Penalized Regression Models for Biological Data," Mathematics, MDPI, vol. 10(19), pages 1-24, October.
    13. Zakariya Yahya Algamal & Muhammad Hisyam Lee, 2019. "A two-stage sparse logistic regression for optimal gene selection in high-dimensional microarray data classification," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 13(3), pages 753-771, September.
    14. Dai, Linlin & Chen, Kani & Sun, Zhihua & Liu, Zhenqiu & Li, Gang, 2018. "Broken adaptive ridge regression and its asymptotic properties," Journal of Multivariate Analysis, Elsevier, vol. 168(C), pages 334-351.
    15. Posch, Konstantin & Arbeiter, Maximilian & Pilz, Juergen, 2020. "A novel Bayesian approach for variable selection in linear regression models," Computational Statistics & Data Analysis, Elsevier, vol. 144(C).
    16. Tanin Sirimongkolkasem & Reza Drikvandi, 2019. "On Regularisation Methods for Analysis of High Dimensional Data," Annals of Data Science, Springer, vol. 6(4), pages 737-763, December.
    17. Fang, Xiaolei & Paynabar, Kamran & Gebraeel, Nagi, 2017. "Multistream sensor fusion-based prognostics model for systems with single failure modes," Reliability Engineering and System Safety, Elsevier, vol. 159(C), pages 322-331.
    18. Siwei Xia & Yuehan Yang & Hu Yang, 2022. "Sparse Laplacian Shrinkage with the Graphical Lasso Estimator for Regression Problems," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 31(1), pages 255-277, March.
    19. Hui Xiao & Yiguo Sun, 2019. "On Tuning Parameter Selection in Model Selection and Model Averaging: A Monte Carlo Study," JRFM, MDPI, vol. 12(3), pages 1-16, June.
    20. Daniel, Jeffrey & Horrocks, Julie & Umphrey, Gary J., 2018. "Penalized composite likelihoods for inhomogeneous Gibbs point process models," Computational Statistics & Data Analysis, Elsevier, vol. 124(C), pages 104-116.

    More about this item

    Keywords

    Bigdata; Data Science; Deep learning; Financial regulation; Credit risk;
    All these keywords.

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:hal:cesptp:halshs-01719983. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: CCSD (email available below). General contact details of provider: https://hal.archives-ouvertes.fr/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.