IDEAS home Printed from https://ideas.repec.org/a/eee/finsta/v49y2020ics1572308920300243.html
   My bibliography  Save this article

Predicting systemic financial crises with recurrent neural networks

Author

Listed:
  • Tölö, Eero

Abstract

We consider predicting systemic financial crises one to five years ahead using recurrent neural networks. We evaluate the prediction performance with the Jórda-Schularick-Taylor dataset, which includes the crisis dates and annual macroeconomic series of 17 countries over the period 1870−2016. Previous literature has found that simple neural net architectures are useful and outperform the traditional logistic regression model in predicting systemic financial crises. We show that such predictions can be significantly improved by making use of the Long-Short Term Memory (RNN-LSTM) and the Gated Recurrent Unit (RNN-GRU) neural nets. Behind the success is the recurrent networks’ ability to make more robust predictions from the time series data. The results remain robust after extensive sensitivity analysis.

Suggested Citation

  • Tölö, Eero, 2020. "Predicting systemic financial crises with recurrent neural networks," Journal of Financial Stability, Elsevier, vol. 49(C).
  • Handle: RePEc:eee:finsta:v:49:y:2020:i:c:s1572308920300243
    DOI: 10.1016/j.jfs.2020.100746
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1572308920300243
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.jfs.2020.100746?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Jürgen Von Hagen & Tai‐Kuang Ho, 2007. "Money Market Pressure and the Determinants of Banking Crises," Journal of Money, Credit and Banking, Blackwell Publishing, vol. 39(5), pages 1037-1066, August.
    2. Binner, Jane M. & Elger, C. Thomas & Nilsson, Birger & Tepper, Jonathan A., 2006. "Predictable non-linearities in U.S. inflation," Economics Letters, Elsevier, vol. 93(3), pages 323-328, December.
    3. Katharina Knoll & Moritz Schularick & Thomas Steger, 2017. "No Price Like Home: Global House Prices, 1870-2012," American Economic Review, American Economic Association, vol. 107(2), pages 331-353, February.
    4. Domac, Ilker & Martinez Peria, Maria Soledad, 2003. "Banking crises and exchange rate regimes: is there a link?," Journal of International Economics, Elsevier, vol. 61(1), pages 41-72, October.
    5. Òscar Jordà & Moritz Schularick & Alan M. Taylor, 2017. "Macrofinancial History and the New Business Cycle Facts," NBER Macroeconomics Annual, University of Chicago Press, vol. 31(1), pages 213-263.
    6. Alessi, Lucia & Detken, Carsten, 2018. "Identifying excessive credit growth and leverage," Journal of Financial Stability, Elsevier, vol. 35(C), pages 215-225.
    7. Carmen M. Reinhart & Graciela L. Kaminsky, 1999. "The Twin Crises: The Causes of Banking and Balance-of-Payments Problems," American Economic Review, American Economic Association, vol. 89(3), pages 473-500, June.
    8. Moritz Schularick & Alan M. Taylor, 2012. "Credit Booms Gone Bust: Monetary Policy, Leverage Cycles, and Financial Crises, 1870-2008," American Economic Review, American Economic Association, vol. 102(2), pages 1029-1061, April.
    9. Drehmann, Mathias & Juselius, Mikael, 2014. "Evaluating early warning indicators of banking crises: Satisfying policy requirements," International Journal of Forecasting, Elsevier, vol. 30(3), pages 759-780.
    10. Carmen M. Reinhart & Kenneth S. Rogoff, 2014. "This Time is Different: A Panoramic View of Eight Centuries of Financial Crises," Annals of Economics and Finance, Society for AEF, vol. 15(2), pages 215-268, November.
    11. Qi, Min, 2001. "Predicting US recessions with leading indicators via neural network models," International Journal of Forecasting, Elsevier, vol. 17(3), pages 383-401.
    12. Babecký, Jan & Havránek, Tomáš & Matějů, Jakub & Rusnák, Marek & Šmídková, Kateřina & Vašíček, Bořek, 2014. "Banking, debt, and currency crises in developed countries: Stylized facts and early warning indicators," Journal of Financial Stability, Elsevier, vol. 15(C), pages 1-17.
    13. Carmen M. Reinhart & Graciela L. Kaminsky, 1999. "The Twin Crises: The Causes of Banking and Balance-of-Payments Problems," American Economic Review, American Economic Association, vol. 89(3), pages 473-500, June.
    14. P. Manasse & R. Savona & M. Vezzoli, 2013. "Rules of Thumb for Banking Crises in Emerging Markets," Working Papers wp872, Dipartimento Scienze Economiche, Universita' di Bologna.
    15. Barrell, Ray & Davis, E. Philip & Karim, Dilruba & Liadze, Iana, 2011. "How Idiosyncratic are Banking Crises in OECD Countries?," National Institute Economic Review, Cambridge University Press, vol. 216, pages 53-58, April.
    16. Fioramanti, Marco, 2008. "Predicting sovereign debt crises using artificial neural networks: A comparative approach," Journal of Financial Stability, Elsevier, vol. 4(2), pages 149-164, June.
    17. Casabianca, Elizabeth Jane & Catalano, Michele & Forni, Lorenzo & Giarda, Elena & Passeri, Simone, 2022. "A machine learning approach to rank the determinants of banking crises over time and across countries," Journal of International Money and Finance, Elsevier, vol. 129(C).
    18. Kauko, Karlo, 2012. "External deficits and non-performing loans in the recent financial crisis," Economics Letters, Elsevier, vol. 115(2), pages 196-199.
    19. Detken, Carsten & Weeken, Olaf & Alessi, Lucia & Bonfim, Diana & Boucinha, Miguel & Castro, Christian & Frontczak, Sebastian & Giordana, Gaston & Giese, Julia & Wildmann, Nadya & Kakes, Jan & Klaus, B, 2014. "Operationalising the countercyclical capital buffer: indicator selection, threshold identification and calibration options," ESRB Occasional Paper Series 5, European Systemic Risk Board.
    20. Andrew Filardo & Marco Jacopo Lombardi & Marek Raczko, 2018. "Measuring financial cycle time," BIS Working Papers 755, Bank for International Settlements.
    21. Carmen M. Reinhart & Kenneth S. Rogoff, 2009. "Varieties of Crises and Their Dates," Introductory Chapters, in: This Time Is Different: Eight Centuries of Financial Folly, Princeton University Press.
    22. Bluwstein, Kristina & Buckmann, Marcus & Joseph, Andreas & Kang, Miao & Kapadia, Sujit & Simsek, Özgür, 2020. "Credit growth, the yield curve and financial crisis prediction: evidence from a machine learning approach," Bank of England working papers 848, Bank of England.
    23. Bordo, Michael D. & Meissner, Christopher M., 2012. "Does inequality lead to a financial crisis?," Journal of International Money and Finance, Elsevier, vol. 31(8), pages 2147-2161.
    24. Periklis Gogas & Theophilos Papadimitriou & Maria Matthaiou & Efthymia Chrysanthidou, 2015. "Yield Curve and Recession Forecasting in a Machine Learning Framework," Computational Economics, Springer;Society for Computational Economics, vol. 45(4), pages 635-645, April.
    25. Lang, Jan Hannes & Izzo, Cosimo & Fahr, Stephan & Ruzicka, Josef, 2019. "Anticipating the bust: a new cyclical systemic risk indicator to assess the likelihood and severity of financial crises," Occasional Paper Series 219, European Central Bank.
    26. Thomas R. Cook & Aaron Smalter Hall, 2017. "Macroeconomic Indicator Forecasting with Deep Neural Networks," Research Working Paper RWP 17-11, Federal Reserve Bank of Kansas City.
    27. Alessi, Lucia & Detken, Carsten, 2011. "Quasi real time early warning indicators for costly asset price boom/bust cycles: A role for global liquidity," European Journal of Political Economy, Elsevier, vol. 27(3), pages 520-533, September.
    28. Caggiano, Giovanni & Calice, Pietro & Leonida, Leone & Kapetanios, George, 2016. "Comparing logit-based early warning systems: Does the duration of systemic banking crises matter?," Journal of Empirical Finance, Elsevier, vol. 37(C), pages 104-116.
    29. Kim Ristolainen, 2018. "Predicting Banking Crises with Artificial Neural Networks: The Role of Nonlinearity and Heterogeneity," Scandinavian Journal of Economics, Wiley Blackwell, vol. 120(1), pages 31-62, January.
    30. Andrew Berg & Catherine Pattillo, 1999. "Are Currency Crises Predictable? A Test," IMF Staff Papers, Palgrave Macmillan, vol. 46(2), pages 1-1.
    31. Rickard Nyman & Paul Ormerod, 2017. "Predicting Economic Recessions Using Machine Learning Algorithms," Papers 1701.01428, arXiv.org.
    32. Markus Holopainen & Peter Sarlin, 2017. "Toward robust early-warning models: a horse race, ensembles and model uncertainty," Quantitative Finance, Taylor & Francis Journals, vol. 17(12), pages 1933-1963, December.
    33. Davis, E. Philip & Karim, Dilruba, 2008. "Comparing early warning systems for banking crises," Journal of Financial Stability, Elsevier, vol. 4(2), pages 89-120, June.
    34. Suss, Joel & Treitel, Henry, 2019. "Predicting bank distress in the UK with machine learning," Bank of England working papers 831, Bank of England.
    35. Claudio Borio, 2014. "The financial cycle and macroeconomics: what have we learned and what are the policy implications?," Chapters, in: Ewald Nowotny & Doris Ritzberger-Grünwald & Peter Backé (ed.), Financial Cycles and the Real Economy, chapter 2, pages 10-35, Edward Elgar Publishing.
    36. Mark Joy & Marek Rusnák & Kateřina Šmídková & Bořek Vašíček, 2017. "Banking and Currency Crises: Differential Diagnostics for Developed Countries," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 22(1), pages 44-67, January.
    37. Eero Tölö & Helinä Laakkonen & Simo Kalatie, 2018. "Evaluating Indicators for Use in Setting the Countercyclical Capital Buffer," International Journal of Central Banking, International Journal of Central Banking, vol. 14(2), pages 51-112, March.
    38. Bussiere, Matthieu & Fratzscher, Marcel, 2006. "Towards a new early warning system of financial crises," Journal of International Money and Finance, Elsevier, vol. 25(6), pages 953-973, October.
    39. Caggiano, Giovanni & Calice, Pietro & Leonida, Leone, 2014. "Early warning systems and systemic banking crises in low income countries: A multinomial logit approach," Journal of Banking & Finance, Elsevier, vol. 47(C), pages 258-269.
    40. Detken, Carsten & Peltonen, Tuomas A. & Schudel, Willem & Behn, Markus, 2013. "Setting countercyclical capital buffers based on early warning models: would it work?," Working Paper Series 1604, European Central Bank.
    41. Claudio Borio & Mathias Drehmann, 2009. "Assessing the risk of banking crises - revisited," BIS Quarterly Review, Bank for International Settlements, March.
    42. Roy, Saktinil & Kemme, David M., 2012. "Causes of banking crises: Deregulation, credit booms and asset bubbles, then and now," International Review of Economics & Finance, Elsevier, vol. 24(C), pages 270-294.
    43. Mathias Drehmann & Claudio Borio & Leonardo Gambacorta & Gabriel Jiminez & Carlos Trucharte, 2010. "Countercyclical capital buffers: exploring options," BIS Working Papers 317, Bank for International Settlements.
    44. Borio, Claudio, 2014. "The financial cycle and macroeconomics: What have we learnt?," Journal of Banking & Finance, Elsevier, vol. 45(C), pages 182-198.
    45. E. Davis & Dilruba Karim & Iana Liadze, 2011. "Should multivariate early warning systems for banking crises pool across regions?," Review of World Economics (Weltwirtschaftliches Archiv), Springer;Institut für Weltwirtschaft (Kiel Institute for the World Economy), vol. 147(4), pages 693-716, November.
    46. Demirguc, Asli & Detragiache, Enrica, 2000. "Monitoring Banking Sector Fragility: A Multivariate Logit Approach," The World Bank Economic Review, World Bank Group, vol. 14(2), pages 287-307, May.
    47. Claudio Borio & Philip Lowe, 2002. "Assessing the risk of banking crises," BIS Quarterly Review, Bank for International Settlements, December.
    48. Daniel C. Hardy & Ceyla Pazarbasioglu, 1999. "Determinants and Leading Indicators of Banking Crises: Further Evidence," IMF Staff Papers, Palgrave Macmillan, vol. 46(3), pages 1-1.
    49. Svetlana Borovkova & Ioannis Tsiamas, 2019. "An ensemble of LSTM neural networks for high‐frequency stock market classification," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 38(6), pages 600-619, September.
    50. Carsten Detken & Olaf Weeken & Lucia Alessi & Diana Bonfim & Miguel M. Boucinha & Christian Castro & Sebastian Frontczak & Gaston Giordana & Julia Giese & Nadya Jahn & Jan Kakes & Benjamin Klaus & Jan, 2014. "Operationalising the countercyclical capital buffer: indicator selection, threshold identification and calibration options," ESRB Occasional Paper Series 05, European Systemic Risk Board.
    51. Beutel, Johannes & List, Sophia & von Schweinitz, Gregor, 2019. "Does machine learning help us predict banking crises?," Journal of Financial Stability, Elsevier, vol. 45(C).
    52. Kauko, Karlo, 2014. "How to foresee banking crises? A survey of the empirical literature," Economic Systems, Elsevier, vol. 38(3), pages 289-308.
    53. Mr. Luc Laeven & Mr. Fabian Valencia, 2012. "Systemic Banking Crises Database: An Update," IMF Working Papers 2012/163, International Monetary Fund.
    54. Alessi, Lucia & Antunes, Antonio & Babecky, Jan & Baltussen, Simon & Behn, Markus & Bonfim, Diana & Bush, Oliver & Detken, Carsten & Frost, Jon & Guimaraes, Rodrigo & Havranek, Tomas & Joy, Mark & Kau, 2015. "Comparing different early warning systems: Results from a horse race competition among members of the Macro-prudential Research Network," MPRA Paper 62194, University Library of Munich, Germany.
    55. Duttagupta, Rupa & Cashin, Paul, 2011. "Anatomy of banking crises in developing and emerging market countries," Journal of International Money and Finance, Elsevier, vol. 30(2), pages 354-376, March.
    56. Büyükkarabacak, Berrak & Valev, Neven T., 2010. "The role of household and business credit in banking crises," Journal of Banking & Finance, Elsevier, vol. 34(6), pages 1247-1256, June.
    57. Asli Demirgüç-Kunt & Enrica Detragiache, 1998. "The Determinants of Banking Crises in Developing and Developed Countries," IMF Staff Papers, Palgrave Macmillan, vol. 45(1), pages 81-109, March.
    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. Buckmann, Marcus & Haldane, Andy & Hüser, Anne-Caroline, 2021. "Comparing minds and machines: implications for financial stability," Bank of England working papers 937, Bank of England.

    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. repec:zbw:bofrdp:2019_014 is not listed on IDEAS
    2. Tölö, Eero, 2019. "Predicting systemic financial crises with recurrent neural networks," Research Discussion Papers 14/2019, Bank of Finland.
    3. Tölö, Eero, 2019. "Predicting systemic financial crises with recurrent neural networks," Bank of Finland Research Discussion Papers 14/2019, Bank of Finland.
    4. Kauko, Karlo, 2014. "How to foresee banking crises? A survey of the empirical literature," Economic Systems, Elsevier, vol. 38(3), pages 289-308.
    5. Casabianca, Elizabeth Jane & Catalano, Michele & Forni, Lorenzo & Giarda, Elena & Passeri, Simone, 2022. "A machine learning approach to rank the determinants of banking crises over time and across countries," Journal of International Money and Finance, Elsevier, vol. 129(C).
    6. Fendel Ralf & Stremmel Hanno, 2016. "Characteristics of Banking Crises: A Comparative Study with Geographical Contagion," Journal of Economics and Statistics (Jahrbuecher fuer Nationaloekonomie und Statistik), De Gruyter, vol. 236(3), pages 349-388, May.
    7. Alessi, Lucia & Detken, Carsten, 2018. "Identifying excessive credit growth and leverage," Journal of Financial Stability, Elsevier, vol. 35(C), pages 215-225.
    8. Antulov-Fantulin, Nino & Lagravinese, Raffaele & Resce, Giuliano, 2021. "Predicting bankruptcy of local government: A machine learning approach," Journal of Economic Behavior & Organization, Elsevier, vol. 183(C), pages 681-699.
    9. Hamdaoui, Mekki, 2016. "Are systemic banking crises in developed and developing countries predictable?," Journal of Multinational Financial Management, Elsevier, vol. 37, pages 114-138.
    10. Lainà, Patrizio & Nyholm, Juho & Sarlin, Peter, 2015. "Leading indicators of systemic banking crises: Finland in a panel of EU countries," Review of Financial Economics, Elsevier, vol. 24(C), pages 18-35.
    11. Tran Huynh & Silke Ãœbelmesser, 2022. "Early warning models for systemic banking crises: can political indicators improve prediction?," Jena Economics Research Papers 2022-007, Friedrich-Schiller-University Jena.
    12. Hartwig, Benny & Meinerding, Christoph & Schüler, Yves S., 2021. "Identifying indicators of systemic risk," Journal of International Economics, Elsevier, vol. 132(C).
    13. Antunes, António & Bonfim, Diana & Monteiro, Nuno & Rodrigues, Paulo M.M., 2018. "Forecasting banking crises with dynamic panel probit models," International Journal of Forecasting, Elsevier, vol. 34(2), pages 249-275.
    14. Audit, Dooneshsingh & Alam, Nafis, 2022. "Why have credit variables taken centre stage in predicting systemic banking crises?," Latin American Journal of Central Banking (previously Monetaria), Elsevier, vol. 3(1).
    15. Mathonnat, Clément & Minea, Alexandru, 2018. "Financial development and the occurrence of banking crises," Journal of Banking & Finance, Elsevier, vol. 96(C), pages 344-354.
    16. Kalatie, Simo & Laakkonen, Helinä & Tölö, Eero, 2015. "Indicators used in setting the countercyclical capital buffer," Bank of Finland Research Discussion Papers 8/2015, Bank of Finland.
    17. Lanbiao Liu & Chen Chen & Bo Wang, 2022. "Predicting financial crises with machine learning methods," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 41(5), pages 871-910, August.
    18. Caggiano, Giovanni & Calice, Pietro & Leonida, Leone & Kapetanios, George, 2016. "Comparing logit-based early warning systems: Does the duration of systemic banking crises matter?," Journal of Empirical Finance, Elsevier, vol. 37(C), pages 104-116.
    19. Filippopoulou, Chryssanthi & Galariotis, Emilios & Spyrou, Spyros, 2020. "An early warning system for predicting systemic banking crises in the Eurozone: A logit regression approach," Journal of Economic Behavior & Organization, Elsevier, vol. 172(C), pages 344-363.
    20. Kalatie, Simo & Laakkonen, Helinä & Tölö, Eero, 2015. "Indicators used in setting the countercyclical capital buffer," Research Discussion Papers 8/2015, Bank of Finland.
    21. repec:zbw:bofrdp:2015_008 is not listed on IDEAS
    22. Virtanen, Timo & Tölö, Eero & Virén, Matti & Taipalus, Katja, 2018. "Can bubble theory foresee banking crises?," Journal of Financial Stability, Elsevier, vol. 36(C), pages 66-81.

    More about this item

    Keywords

    Early warning system; Systemic Banking crises; Neural networks; Validation;
    All these keywords.

    JEL classification:

    • G21 - Financial Economics - - Financial Institutions and Services - - - Banks; Other Depository Institutions; Micro Finance Institutions; Mortgages
    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
    • C52 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Model Evaluation, Validation, and Selection

    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:eee:finsta:v:49:y:2020:i:c:s1572308920300243. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: . General contact details of provider: http://www.elsevier.com/locate/jfstabil .

    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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/jfstabil .

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

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.