IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2410.02846.html
   My bibliography  Save this paper

A Spatio-Temporal Machine Learning Model for Mortgage Credit Risk: Default Probabilities and Loan Portfolios

Author

Listed:
  • Pascal Kundig
  • Fabio Sigrist

Abstract

We introduce a novel machine learning model for credit risk by combining tree-boosting with a latent spatio-temporal Gaussian process model accounting for frailty correlation. This allows for modeling non-linearities and interactions among predictor variables in a flexible data-driven manner and for accounting for spatio-temporal variation that is not explained by observable predictor variables. We also show how estimation and prediction can be done in a computationally efficient manner. In an application to a large U.S. mortgage credit risk data set, we find that both predictive default probabilities for individual loans and predictive loan portfolio loss distributions obtained with our novel approach are more accurate compared to conventional independent linear hazard models and also linear spatio-temporal models. Using interpretability tools for machine learning models, we find that the likely reasons for this outperformance are strong interaction and non-linear effects in the predictor variables and the presence of large spatio-temporal frailty effects.

Suggested Citation

  • Pascal Kundig & Fabio Sigrist, 2024. "A Spatio-Temporal Machine Learning Model for Mortgage Credit Risk: Default Probabilities and Loan Portfolios," Papers 2410.02846, arXiv.org.
  • Handle: RePEc:arx:papers:2410.02846
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2410.02846
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Berloco, Claudia & Argiento, Raffaele & Montagna, Silvia, 2023. "Forecasting short-term defaults of firms in a commercial network via Bayesian spatial and spatio-temporal methods," International Journal of Forecasting, Elsevier, vol. 39(3), pages 1065-1077.
    2. Calabrese, Raffaella & Dombrowski, Timothy & Mandel, Antoine & Pace, R. Kelley & Zanin, Luca, 2024. "Impacts of extreme weather events on mortgage risks and their evolution under climate change: A case study on Florida," European Journal of Operational Research, Elsevier, vol. 314(1), pages 377-392.
    3. Darrell Duffie & Andreas Eckner & Guillaume Horel & Leandro Saita, 2009. "Frailty Correlated Default," Journal of Finance, American Finance Association, vol. 64(5), pages 2089-2123, October.
    4. Abhirup Datta & Sudipto Banerjee & Andrew O. Finley & Alan E. Gelfand, 2016. "Hierarchical Nearest-Neighbor Gaussian Process Models for Large Geostatistical Datasets," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 111(514), pages 800-812, April.
    5. Gneiting, Tilmann & Raftery, Adrian E., 2007. "Strictly Proper Scoring Rules, Prediction, and Estimation," Journal of the American Statistical Association, American Statistical Association, vol. 102, pages 359-378, March.
    6. Babii, Andrii & Chen, Xi & Ghysels, Eric, 2019. "Commercial and Residential Mortgage Defaults: Spatial Dependence with Frailty," Journal of Econometrics, Elsevier, vol. 212(1), pages 47-77.
    7. Edward I. Altman, 1968. "Financial Ratios, Discriminant Analysis And The Prediction Of Corporate Bankruptcy," Journal of Finance, American Finance Association, vol. 23(4), pages 589-609, September.
    8. Raffaella Calabrese & Galina Andreeva & Jake Ansell, 2019. "“Birds of a Feather” Fail Together: Exploring the Nature of Dependency in SME Defaults," Risk Analysis, John Wiley & Sons, vol. 39(1), pages 71-84, January.
    9. Sigrist, Fabio & Hirnschall, Christoph, 2019. "Grabit: Gradient tree-boosted Tobit models for default prediction," Journal of Banking & Finance, Elsevier, vol. 102(C), pages 177-192.
    10. Calabrese, Raffaella & Crook, Jonathan, 2020. "Spatial contagion in mortgage defaults: A spatial dynamic survival model with time and space varying coefficients," European Journal of Operational Research, Elsevier, vol. 287(2), pages 749-761.
    11. Andrew F. Haughwout & Donghoon Lee & Joseph Tracy & Wilbert Van der Klaauw, 2011. "Real estate investors, the leverage cycle, and the housing market crisis," Staff Reports 514, Federal Reserve Bank of New York.
    12. Sigrist, Fabio & Leuenberger, Nicola, 2023. "Machine learning for corporate default risk: Multi-period prediction, frailty correlation, loan portfolios, and tail probabilities," European Journal of Operational Research, Elsevier, vol. 305(3), pages 1390-1406.
    13. Shumway, Tyler, 2001. "Forecasting Bankruptcy More Accurately: A Simple Hazard Model," The Journal of Business, University of Chicago Press, vol. 74(1), pages 101-124, January.
    14. Medina-Olivares, Victor & Calabrese, Raffaella & Dong, Yizhe & Shi, Baofeng, 2022. "Spatial dependence in microfinance credit default," International Journal of Forecasting, Elsevier, vol. 38(3), pages 1071-1085.
    15. Koopman, Siem Jan & Lucas, André & Schwaab, Bernd, 2011. "Modeling frailty-correlated defaults using many macroeconomic covariates," Journal of Econometrics, Elsevier, vol. 162(2), pages 312-325, June.
    16. Wenbin Hu & Junzi Zhou, 2019. "Joint modeling: an application in behavioural scoring," Journal of the Operational Research Society, Taylor & Francis Journals, vol. 70(7), pages 1129-1139, July.
    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. Sigrist, Fabio & Leuenberger, Nicola, 2023. "Machine learning for corporate default risk: Multi-period prediction, frailty correlation, loan portfolios, and tail probabilities," European Journal of Operational Research, Elsevier, vol. 305(3), pages 1390-1406.
    2. Mark Clintworth & Dimitrios Lyridis & Evangelos Boulougouris, 2023. "Financial risk assessment in shipping: a holistic machine learning based methodology," Maritime Economics & Logistics, Palgrave Macmillan;International Association of Maritime Economists (IAME), vol. 25(1), pages 90-121, March.
    3. Nguyen, Ha, 2023. "An empirical application of Particle Markov Chain Monte Carlo to frailty correlated default models," Journal of Empirical Finance, Elsevier, vol. 72(C), pages 103-121.
    4. Qi, Min & Zhang, Xiaofei & Zhao, Xinlei, 2014. "Unobserved systematic risk factor and default prediction," Journal of Banking & Finance, Elsevier, vol. 49(C), pages 216-227.
    5. Ha Nguyen, 2023. "Particle MCMC in forecasting frailty correlated default models with expert opinion," Papers 2304.11586, arXiv.org, revised Aug 2023.
    6. Chen, Peimin & Wu, Chunchi, 2014. "Default prediction with dynamic sectoral and macroeconomic frailties," Journal of Banking & Finance, Elsevier, vol. 40(C), pages 211-226.
    7. Anna Dubinova & Andre Lucas & Sean Telg, 2021. "COVID-19, Credit Risk and Macro Fundamentals," Tinbergen Institute Discussion Papers 21-059/III, Tinbergen Institute.
    8. Ruey-Ching Hwang & Huimin Chung & Jiun-Yi Ku, 2013. "Predicting Recurrent Financial Distresses with Autocorrelation Structure: An Empirical Analysis from an Emerging Market," Journal of Financial Services Research, Springer;Western Finance Association, vol. 43(3), pages 321-341, June.
    9. Asis, Gonzalo & Chari, Anusha & Haas, Adam, 2021. "In search of distress risk in emerging markets," Journal of International Economics, Elsevier, vol. 131(C).
    10. Wenlang Zhang & Gaofeng Han & Steven Chan, 2014. "How Strong are the Linkages between Real Estate and Other Sectors in China?," Working Papers 112014, Hong Kong Institute for Monetary Research.
    11. Anand Deo & Sandeep Juneja, 2021. "Credit Risk: Simple Closed-Form Approximate Maximum Likelihood Estimator," Operations Research, INFORMS, vol. 69(2), pages 361-379, March.
    12. Zhang, Xuan & Ouyang, Ruolan & Liu, Ding & Xu, Liao, 2020. "Determinants of corporate default risk in China: The role of financial constraints," Economic Modelling, Elsevier, vol. 92(C), pages 87-98.
    13. Lando, David & Nielsen, Mads Stenbo, 2010. "Correlation in corporate defaults: Contagion or conditional independence?," Journal of Financial Intermediation, Elsevier, vol. 19(3), pages 355-372, July.
    14. Ye, Xiaoxia & Yu, Fan & Zhao, Ran, 2022. "Credit derivatives and corporate default prediction," Journal of Banking & Finance, Elsevier, vol. 138(C).
    15. Bátiz-Zuk Enrique & Mohamed Abdulkadir & Sánchez-Cajal Fátima, 2021. "Exploring the sources of loan default clustering using survival analysis with frailty," Working Papers 2021-14, Banco de México.
    16. Lei, Jin & Qiu, Jiaping & Wan, Chi & Yu, Fan, 2021. "Credit risk spillovers and cash holdings," Journal of Corporate Finance, Elsevier, vol. 68(C).
    17. Haipeng Xing & Yang Yu, 2018. "Firm’s Credit Risk in the Presence of Market Structural Breaks," Risks, MDPI, vol. 6(4), pages 1-16, December.
    18. Jingjing Long & Cuiqing Jiang & Stanko Dimitrov & Zhao Wang, 2022. "Clues from networks: quantifying relational risk for credit risk evaluation of SMEs," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 8(1), pages 1-41, December.
    19. Stewart Jones, 2017. "Corporate bankruptcy prediction: a high dimensional analysis," Review of Accounting Studies, Springer, vol. 22(3), pages 1366-1422, September.
    20. Victor Medina-Olivares & Finn Lindgren & Raffaella Calabrese & Jonathan Crook, 2023. "Joint model for longitudinal and spatio-temporal survival data," Papers 2311.04008, arXiv.org.

    More about this item

    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:arx:papers:2410.02846. 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    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.