Predicting systemic financial crises with recurrent neural networks

Journal of Financial Stability - Tập 49 - Trang 100746 - 2020
Eero Tölö1,2,3
1Department of Economics, London School of Economics and Political Science, Houghton Street, WC2A 2AE, London, United Kingdom
2Department of Financial Stability, Bank of Finland, P.O. Box 160, FI-00101, Helsinki, Finland
3Helsinki GSE, University of Helsinki, P.O. Box 17, 00014, Finland

Tóm tắt

Từ khóa


Tài liệu tham khảo

Alessi, 2011, Quasi real time early warning indicators for costly asset price boom/bust cycles: a role for global liquidity, Eur. J. Polit. Econ., 27, 520, 10.1016/j.ejpoleco.2011.01.003

Alessi, 2018, Identifying excessive credit growth and leverage, J. Financ. Stab., 35, 215, 10.1016/j.jfs.2017.06.005

Alessi, 2015

Apel, 2019, How much information do monetary policy committees disclose?

Babecký, 2014, Banking, debt and currency crises in developed countries: stylized facts and early warning indicators, J. Financ. Stab., 15, 1, 10.1016/j.jfs.2014.07.001

Barrell, 2011, How idiosyncratic are banking crises in OECD countries?, Inst. Econ. Rev., 216, R53, 10.1177/0027950111411382

Barron, 1993, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Trans. Inf. Theory, 39, 930, 10.1109/18.256500

Basel Committee on Banking Supervision (BCBS), 2011

Behn, 2013

Berg, 1999, Are currency crises predictable? A test, IMF Staff Papers, 46, 1, 10.2307/3867664

Beutel, 2019, Does machine learning help us predict banking crises?, J. Financ. Stab., 45, 10.1016/j.jfs.2019.100693

Binner, 2004, Tools for non-linear time series forecasting in economics – an empirical comparison of regime switching vector autoregressive models and recurrent neural networks, Adv. Econometrics, 19, 71, 10.1016/S0731-9053(04)19003-8

Binner, 2006, Predictable non-linearities in U.S. Inflation, Econ. Lett., 93, 323, 10.1016/j.econlet.2006.06.001

Bluwstein, 2020, Credit growth, the yield curve and financial crisis prediction: evidence from a machine learning approach, Bank of England Staff Working Paper No. 848

Bordo, 2012, Does inequality lead to a financial crisis?, J. Int. Money Finance, 31, 2147, 10.1016/j.jimonfin.2012.05.006

Borio, 2014, The financial cycle and macroeconomics: What have we learnt?, J. Bank. Financ., 45, 182, 10.1016/j.jbankfin.2013.07.031

Borio, 2009, 29

Borio, 2002

Borovkova, 2019, An ensemble of LSTM neural networks for high-frequency stock market classification, J. Forecast., 38, 600, 10.1002/for.2585

Bussiere, 2006, Towards a new early warning system of financial crises, J. Int. Money Finance, 25, 953, 10.1016/j.jimonfin.2006.07.007

Büyükkarabacak, 2010, The role of household and business credit in banking crises, J. Bank. Financ., 34, 1247, 10.1016/j.jbankfin.2009.11.022

Caggiano, 2014, Early warning systems and systemic banking crises in low income countries: a multinomial logit approach, J. Bank. Financ., 47, 258, 10.1016/j.jbankfin.2014.07.002

Caggiano, 2016, Comparing logit-based early warning systems: Does the duration of systemic banking crises matter?, J. Empir. Finance, 37, 104, 10.1016/j.jempfin.2016.01.005

Caprio, 1997, Bank insolvencies: Bad luck, Bad policy, or Bad Banking?, Annual World, Bank Conference on Development Economics

Casabianca, 2019, An early warning system for banking crises: from regression-based analysis to machine learning techniques, Marco Fanno Working Papers 235

Cho, 2014, Learning phrase representations using RNN encoder-decoder for statistical machine translation, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1724, 10.3115/v1/D14-1179

Cook, 2017, Macroeconomic indicator forecasting with deep neural networks, Federal reserve Bank of Kansas City, Research Working Paper 17-11, September

Davis, 2008, Comparing early warning systems for banking crises, J. Financ. Stab., 4, 89, 10.1016/j.jfs.2007.12.004

Davis, 2011, Should Multivariate Early Warning Systems for Banking Crises Pool Across Regions?, Rev. World Econ., 147, 693, 10.1007/s10290-011-0102-1

DeGroot, 1983, The comparison and evaluation of forecasters, Statistician, 32, 12, 10.2307/2987588

DeLong, 1988, Comparing the areas under two or more correlated receiver operating characteristics curves: a nonparametric approach, Biometrics, 44, 837, 10.2307/2531595

Demirgüc-Kunt, 1998, The determinants of banking crises in developed countries, IMF Staff Pap., 45, 81, 10.2307/3867330

Demirgüc-Kunt, 2000, Monitoring banking sector fragility: a multivariate logit approach, World Bank Econ. Rev., 14, 287, 10.1093/wber/14.2.287

Detken, 2014, Operationalising the countercyclical capital buffer: indicator selection, threshold identification and calibration options, ERSB Occasional Paper Series No. 5 / June 2014

Díaz-Martínez, 2011, Predicción de crisis financieras mediante conjuntos imprecisos (rough sets) y árboles de decisión, Innovar, 21, 83

Domaç, 2003, Banking crises and exchange rate regimes: is there a link?, J. Int. Econ., 61, 41, 10.1016/S0022-1996(02)00081-8

Drehmann, 2014, Evaluating early warning indicators of banking crises: satisfying policy requirements, Int. J. Forecast., 30, 759, 10.1016/j.ijforecast.2013.10.002

Drehmann, 2010, Countercyclical capital buffers: exploring options, BIS Working Papers 317

Duttagupta, 2011, Anatomy of banking crises in developing and emerging market countries, J. Int. Money Finance, 30, 354, 10.1016/j.jimonfin.2010.08.006

Filardo, 2018, Measuring financial cycle time, BIS Working Papers 755

Fioramanti, 2008, Predicting sovereign debt crises using artificial neural networks: a comparative approach, J. Financ. Stab., 4, 149, 10.1016/j.jfs.2008.01.001

Fischer, 2018, Deep learning with long-short term memory networks for financial marker predictions, Eur. J. Oper. Res., 270, 654, 10.1016/j.ejor.2017.11.054

Fouliard, 2019, Answering the queen: online machine learning and financial crises, Presentation at the BIS Annual Conference

Fricke, 2017

Gers, 2001, Applying LSTM to time series predictable through time-window approaches, International Conference on Artificial Neural Networks ICANN 2001, 669, 10.1007/3-540-44668-0_93

Gers, 2002, Learning precise timing with LSTM recurrent networks, J. Mach. Learn. Res., 3, 115

Gogas, 2014, Yield curve and recession forecasting in a machine learning framework, Comput. Econ., 45, 635, 10.1007/s10614-014-9432-0

Hansen, 1997, Early stop criterion from the bootstrap ensemble, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, 4, 3205, 10.1109/ICASSP.1997.595474

Hardy, 1999, Determinants and leading indicators of banking crises: further evidence, IMF Staff Paper, 46, 1, 10.2307/3867642

Hochreiter, 1997, Long short-term memory, Neural Comput., 9, 1735, 10.1162/neco.1997.9.8.1735

Holopainen, 2017, Toward robust early-warning models: a horse race, ensembles and model uncertainty, Quant. Finance, 17, 1933, 10.1080/14697688.2017.1357972

Hornik, 1991, Approximation capabilities of multilayer feedforward networks, Neural Netw., 4, 251, 10.1016/0893-6080(91)90009-T

Jordà, 2015, Leveraged bubbles, J. Monet. Econ., 76, S1, 10.1016/j.jmoneco.2015.08.005

Jordà, 2017, Macrofinancial history and the New business cycle facts, vol. 31

Joy, 2017, Banking and currency crises: differential diagnostics for developed countries, Int. J. Financ. Econ., 22, 44, 10.1002/ijfe.1570

Kaminsky, 1999, The twin crises: the causes of banking and balance-of-payments problems, Am. Econ. Rev., 89, 473, 10.1257/aer.89.3.473

Kauko, 2012, External deficits and non-performing loans in the recent financial crisis, Econ. Lett., 115, 196, 10.1016/j.econlet.2011.12.018

Kauko, 2014, How to foresee banking crises? A survey of the empirical literature, Econ. Syst., 38, 289, 10.1016/j.ecosys.2014.01.001

Kauko, 2020, On the long-run calibration of the credit-to-GDP gap as a banking crisis predictor, Finnish Economic Papers

Kauko, 2020, Banking crisis prediction with differenced relative credit, Appl. Econ. Q.

Knoll, 2016, No price like home: global house prices 1870-2012, Am. Econ. Rev., 107, 331, 10.1257/aer.20150501

Kuan, 2007, Artificial neural networks: an econometric perspective, Econom. Rev., 13, 1, 10.1080/07474939408800273

Laeven, 2012, Systemic Banking crises database: an update, Working Paper No.12/163

Lang, 2019, Anticipating the bust: a new cyclical systemic risk inidicator to assess the likelihood and severity of financial crises, ECB Occasional Paper Series No. 219

Lo Duca, 2013, Assessing systemic risks and predicting systemic events, J. Bank. Financ., 37, 2183, 10.1016/j.jbankfin.2012.06.010

Lundberg, 2017, A unified approach to interpreting model predictions, Proceedings of the 31st International Conference on Neural Information Processing Systems, 4768

Manasse, 2009, “Rules of thumb” for sovereign debt crises, J. Int. Econ., 78, 192, 10.1016/j.jinteco.2008.12.002

Manasse, 2013, Rules of thumb for Banking crises in emerging markets, Universita’ di Bologna Working Papers No. 872

Minami, 2018, Predicting equity price with corporate action events using RNN-LSTM, J. Math. Financ., 8, 58, 10.4236/jmf.2018.81005

Niculescu-Mizin, 2005, Predicting Good probabilities with supervised learning, ICML 05 Proceedings of the 34th International Conference on Machine Learning, 625, 10.1145/1102351.1102430

Nik, 2016, J. Econ. Cooperation Dev., 37, 25

Nyman, 2017

Olah, 2015

Qi, 2001, Predicting US recessions with leading indicators via neural network models, Int. J. Forecast., 17, 383, 10.1016/S0169-2070(01)00092-9

Reinhart, 2009

Ristolainen, 2018, Predicting banking crises with artificial neural networks: the role of Nonlinearity and heterogeneity, Scand. J. Econ., 120, 31, 10.1111/sjoe.12216

Roy, 2012, Causes of banking crises: deregulation, credit booms and asset bubbles, then and now, Int. Rev. Econ. Financ., 24, 270, 10.1016/j.iref.2012.04.001

Sarlin, 2014, Mapping financial stability, Ai Commun., 27, 285

Schularick, 2012, Credit booms gone bust: monetary policy, leverage cycles and financial crises, 1870-2008, Am. Econ. Rev., 102, 1029, 10.1257/aer.102.2.1029

Shapley, 1953, A value for n-person games, Contributions to the Theory of Games, 2, 307

Siami-Namini, 2018, A comparison of ARIMA and LSTM in forecasting time series, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 1394, 10.1109/ICMLA.2018.00227

Suss, 2019, Predicting bank distress in the UK with machine learning, Bank of England Staff Working Paper No. 831

Tölö, 2018, Evaluating Indicator for use in setting the countercyclical capital buffer, Int. J. Cent. Bank., 14, 51

von Hagen, 2007, Money market pressure and the determinants of banking crises, J. Money Credit Bank., 39, 1037, 10.1111/j.1538-4616.2007.00057.x

Wu, 2016