IDEAS home Printed from https://ideas.repec.org/p/ajf/louvlr/2020002.html
   My bibliography  Save this paper

Forecasting recovery rates on non-performing loans with machine learning

Author

Listed:
  • Bellotti, Anthony
  • Brigo, Damiano
  • Gambetti, Paolo
  • Vrins, Frédéric

Abstract

We compare the performance of a wide set of regression techniques and machine-learning algorithms for predicting recovery rates on non-performing loans, using a private database from a European debt collection agency. We find that rule-based algorithms such as Cubist, boosted trees, and random forests perform significantly better than other approaches. In addition to loan contract specificities, predictors that refer to the bank recovery process — prior to the portfolio’s sale to a debt collector — are also shown to enhance forecasting performance. These variables, derived from the time series of contacts to defaulted clients and client reimbursements to the bank, help all algorithms better identify debtors with different repayment ability and/or commitment, and in general those with different recovery potential.
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract was borrowed from another version of this item.)
(This abstract wa
(This abstract was borrowed from another version of this item.)

Suggested Citation

  • Bellotti, Anthony & Brigo, Damiano & Gambetti, Paolo & Vrins, Frédéric, 2020. "Forecasting recovery rates on non-performing loans with machine learning," LIDAM Reprints LFIN 2020002, Université catholique de Louvain, Louvain Finance (LFIN).
    • Handle: RePEc:ajf:louvlr:2020002
    Note: In : International Journal of Forecasting, Vol. 37, no. 1, p. 428-444
    as

    Download full text from publisher

    To our knowledge, this item is not available for download. To find whether it is available, there are three options:
    1. Check below whether another version of this item is available online.
    2. Check on the provider's web page whether it is in fact available.
    3. Perform a search for a similarly titled item that would be available.

    Other versions of this item:

    References listed on IDEAS

    as
    1. Kuhn, Max, 2008. "Building Predictive Models in R Using the caret Package," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 28(i05).
    2. Gambetti, Paolo & Gauthier, Geneviève & Vrins, Frédéric, 2019. "Recovery rates: Uncertainty certainly matters," Journal of Banking & Finance, Elsevier, vol. 106(C), pages 371-383.
    3. Qi, Min & Yang, Xiaolong, 2009. "Loss given default of high loan-to-value residential mortgages," Journal of Banking & Finance, Elsevier, vol. 33(5), pages 788-799, May.
    4. Scott R. Baker & Nicholas Bloom & Steven J. Davis, 2016. "Measuring Economic Policy Uncertainty," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 131(4), pages 1593-1636.
    5. João Bastos, 2014. "Ensemble Predictions of Recovery Rates," Journal of Financial Services Research, Springer;Western Finance Association, vol. 46(2), pages 177-193, October.
    6. Loterman, Gert & Brown, Iain & Martens, David & Mues, Christophe & Baesens, Bart, 2012. "Benchmarking regression algorithms for loss given default modeling," International Journal of Forecasting, Elsevier, vol. 28(1), pages 161-170.
    7. Gieseck Arne & Largent Yannis, 2016. "The Impact of Macroeconomic Uncertainty on Activity in the Euro Area," Review of Economics, De Gruyter, vol. 67(1), pages 25-52, May.
    8. Peter R. Hansen & Asger Lunde & James M. Nason, 2011. "The Model Confidence Set," Econometrica, Econometric Society, vol. 79(2), pages 453-497, March.
    9. Mauro Bernardi & Leopoldo Catania, 2018. "The model confidence set package for R," International Journal of Computational Economics and Econometrics, Inderscience Enterprises Ltd, vol. 8(2), pages 144-158.
    10. Mee Chi So & Christophe Mues & Adiel T. de Almeida Filho & Lyn C Thomas, 2019. "Debtor level collection operations using Bayesian dynamic programming," Journal of the Operational Research Society, Taylor & Francis Journals, vol. 70(8), pages 1332-1348, August.
    11. Karatzoglou, Alexandros & Smola, Alexandros & Hornik, Kurt & Zeileis, Achim, 2004. "kernlab - An S4 Package for Kernel Methods in R," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 11(i09).
    12. Mindy Leow & Christophe Mues & Lyn Thomas, 2014. "The economy and loss given default: evidence from two UK retail lending data sets," Journal of the Operational Research Society, Palgrave Macmillan;The OR Society, vol. 65(3), pages 363-375, March.
    13. Nazemi, Abdolreza & Heidenreich, Konstantin & Fabozzi, Frank J., 2018. "Improving corporate bond recovery rate prediction using multi-factor support vector regressions," European Journal of Operational Research, Elsevier, vol. 271(2), pages 664-675.
    14. 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).
    15. Hui Ye & Anthony Bellotti, 2019. "Modelling Recovery Rates for Non-Performing Loans," Risks, MDPI, vol. 7(1), pages 1-17, February.
    16. Nazemi, Abdolreza & Fabozzi, Frank J., 2018. "Macroeconomic variable selection for creditor recovery rates," Journal of Banking & Finance, Elsevier, vol. 89(C), pages 14-25.
    17. Bellotti, Tony & Crook, Jonathan, 2012. "Loss given default models incorporating macroeconomic variables for credit cards," International Journal of Forecasting, Elsevier, vol. 28(1), pages 171-182.
    18. Zhang, Jie & Thomas, Lyn C., 2012. "Comparisons of linear regression and survival analysis using single and mixture distributions approaches in modelling LGD," International Journal of Forecasting, Elsevier, vol. 28(1), pages 204-215.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Maria Carannante & Valeria D’Amato & Paola Fersini & Salvatore Forte & Giuseppe Melisi, 2024. "Machine learning due diligence evaluation to increase NPLs profitability transactions on secondary market," Review of Managerial Science, Springer, vol. 18(7), pages 1963-1983, July.
    2. Tanasuica Zotic Coralia, 2024. "A Quantitative Analysis of Default Risk Using Machine Learning and SHAP Value Interpretation," Proceedings of the International Conference on Business Excellence, Sciendo, vol. 18(1), pages 233-245.
    3. Li, Aimin & Li, Zhiyong & Bellotti, Anthony, 2023. "Predicting loss given default of unsecured consumer loans with time-varying survival scores," Pacific-Basin Finance Journal, Elsevier, vol. 78(C).
    4. Nazemi, Abdolreza & Rezazadeh, Hani & Fabozzi, Frank J. & Höchstötter, Markus, 2022. "Deep learning for modeling the collection rate for third-party buyers," International Journal of Forecasting, Elsevier, vol. 38(1), pages 240-252.
    5. Konstantin Gorgen & Abdolreza Nazemi & Melanie Schienle, 2022. "Robust Knockoffs for Controlling False Discoveries With an Application to Bond Recovery Rates," Papers 2206.06026, arXiv.org.
    6. Andrey Koltays & Anton Konev & Alexander Shelupanov, 2021. "Mathematical Model for Choosing Counterparty When Assessing Information Security Risks," Risks, MDPI, vol. 9(7), pages 1-13, July.
    7. Damiano Brigo & Xiaoshan Huang & Andrea Pallavicini & Haitz Saez de Ocariz Borde, 2021. "Interpretability in deep learning for finance: a case study for the Heston model," Papers 2104.09476, arXiv.org.
    8. Kellner, Ralf & Nagl, Maximilian & Rösch, Daniel, 2022. "Opening the black box – Quantile neural networks for loss given default prediction," Journal of Banking & Finance, Elsevier, vol. 134(C).
    9. Marc Gürtler & Marvin Zöllner, 2023. "Heterogeneities among credit risk parameter distributions: the modality defines the best estimation method," OR Spectrum: Quantitative Approaches in Management, Springer;Gesellschaft für Operations Research e.V., vol. 45(1), pages 251-287, March.
    10. Jiajia, Liu & Kun, Guo & Fangcheng, Tang & Yahan, Wang & Shouyang, Wang, 2023. "The effect of the disposal of non-performing loans on interbank liquidity risk in China: A cash flow network-based analysis," The Quarterly Review of Economics and Finance, Elsevier, vol. 89(C), pages 105-119.
    11. Distaso, Walter & Roccazzella, Francesco & Vrins, Frédéric, 2023. "Business cycle and realized losses in the consumer credit industry," LIDAM Discussion Papers LFIN 2023007, Université catholique de Louvain, Louvain Finance (LFIN).
    12. Lisa Crosato & Caterina Liberati & Marco Repetto, 2021. "Look Who's Talking: Interpretable Machine Learning for Assessing Italian SMEs Credit Default," Papers 2108.13914, arXiv.org, revised Sep 2021.
    13. Li, Zhiyong & Li, Aimin & Bellotti, Anthony & Yao, Xiao, 2023. "The profitability of online loans: A competing risks analysis on default and prepayment," European Journal of Operational Research, Elsevier, vol. 306(2), pages 968-985.
    14. González, Marta Ramos & Ureña, Antonio Partal & Fernández-Aguado, Pilar Gómez, 2023. "Forecasting for regulatory credit loss derived from the COVID-19 pandemic: A machine learning approach," Research in International Business and Finance, Elsevier, vol. 64(C).

    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. Paolo Gambetti & Francesco Roccazzella & Frédéric Vrins, 2022. "Meta-Learning Approaches for Recovery Rate Prediction," Risks, MDPI, vol. 10(6), pages 1-29, June.
    2. Distaso, Walter & Roccazzella, Francesco & Vrins, Frédéric, 2023. "Business cycle and realized losses in the consumer credit industry," LIDAM Discussion Papers LFIN 2023007, Université catholique de Louvain, Louvain Finance (LFIN).
    3. Kellner, Ralf & Nagl, Maximilian & Rösch, Daniel, 2022. "Opening the black box – Quantile neural networks for loss given default prediction," Journal of Banking & Finance, Elsevier, vol. 134(C).
    4. Jennifer Betz & Ralf Kellner & Daniel Rösch, 2021. "Time matters: How default resolution times impact final loss rates," Journal of the Royal Statistical Society Series C, Royal Statistical Society, vol. 70(3), pages 619-644, June.
    5. Emily Johnston Ross & Lynn Shibut, 2021. "Loss Given Default, Loan Seasoning and Financial Fragility: Evidence from Commercial Real Estate Loans at Failed Banks," The Journal of Real Estate Finance and Economics, Springer, vol. 63(4), pages 630-661, November.
    6. Li, Aimin & Li, Zhiyong & Bellotti, Anthony, 2023. "Predicting loss given default of unsecured consumer loans with time-varying survival scores," Pacific-Basin Finance Journal, Elsevier, vol. 78(C).
    7. Hurlin, Christophe & Leymarie, Jérémy & Patin, Antoine, 2018. "Loss functions for Loss Given Default model comparison," European Journal of Operational Research, Elsevier, vol. 268(1), pages 348-360.
    8. Sopitpongstorn, Nithi & Silvapulle, Param & Gao, Jiti & Fenech, Jean-Pierre, 2021. "Local logit regression for loan recovery rate," Journal of Banking & Finance, Elsevier, vol. 126(C).
    9. Nazemi, Abdolreza & Baumann, Friedrich & Fabozzi, Frank J., 2022. "Intertemporal defaulted bond recoveries prediction via machine learning," European Journal of Operational Research, Elsevier, vol. 297(3), pages 1162-1177.
    10. Nazemi, Abdolreza & Fatemi Pour, Farnoosh & Heidenreich, Konstantin & Fabozzi, Frank J., 2017. "Fuzzy decision fusion approach for loss-given-default modeling," European Journal of Operational Research, Elsevier, vol. 262(2), pages 780-791.
    11. Xia, Yufei & Zhao, Junhao & He, Lingyun & Li, Yinguo & Yang, Xiaoli, 2021. "Forecasting loss given default for peer-to-peer loans via heterogeneous stacking ensemble approach," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1590-1613.
    12. Kaposty, Florian & Kriebel, Johannes & Löderbusch, Matthias, 2020. "Predicting loss given default in leasing: A closer look at models and variable selection," International Journal of Forecasting, Elsevier, vol. 36(2), pages 248-266.
    13. Pascal François, 2019. "The Determinants of Market-Implied Recovery Rates," Risks, MDPI, vol. 7(2), pages 1-15, May.
    14. Do, Hung Xuan & Rösch, Daniel & Scheule, Harald, 2018. "Predicting loss severities for residential mortgage loans: A three-step selection approach," European Journal of Operational Research, Elsevier, vol. 270(1), pages 246-259.
    15. Thamayanthi Chellathurai, 2017. "Probability Density Of Recovery Rate Given Default Of A Firm’S Debt And Its Constituent Tranches," International Journal of Theoretical and Applied Finance (IJTAF), World Scientific Publishing Co. Pte. Ltd., vol. 20(04), pages 1-34, June.
    16. Štefan Lyócsa & Petra Vašaničová & Branka Hadji Misheva & Marko Dávid Vateha, 2022. "Default or profit scoring credit systems? Evidence from European and US peer-to-peer lending markets," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 8(1), pages 1-21, December.
    17. Tong, Edward N.C. & Mues, Christophe & Thomas, Lyn, 2013. "A zero-adjusted gamma model for mortgage loan loss given default," International Journal of Forecasting, Elsevier, vol. 29(4), pages 548-562.
    18. Nazemi, Abdolreza & Rezazadeh, Hani & Fabozzi, Frank J. & Höchstötter, Markus, 2022. "Deep learning for modeling the collection rate for third-party buyers," International Journal of Forecasting, Elsevier, vol. 38(1), pages 240-252.
    19. Barbagli, Matteo & François, Pascal & Gauthier, Geneviève & Vrins, Frédéric, 2024. "The role of CDS spreads in explaining bond recovery rates," LIDAM Discussion Papers LFIN 2024002, Université catholique de Louvain, Louvain Finance (LFIN).
    20. Miller, Patrick & Töws, Eugen, 2018. "Loss given default adjusted workout processes for leases," Journal of Banking & Finance, Elsevier, vol. 91(C), pages 189-201.

    More about this item

    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:ajf:louvlr:2020002. 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: Séverine De Visscher (email available below). General contact details of provider: https://edirc.repec.org/data/lfuclbe.html .

    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.