IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2207.10539.html
   My bibliography  Save this paper

Estimating value at risk: LSTM vs. GARCH

Author

Listed:
  • Weronika Ormaniec
  • Marcin Pitera
  • Sajad Safarveisi
  • Thorsten Schmidt

Abstract

Estimating value-at-risk on time series data with possibly heteroscedastic dynamics is a highly challenging task. Typically, we face a small data problem in combination with a high degree of non-linearity, causing difficulties for both classical and machine-learning estimation algorithms. In this paper, we propose a novel value-at-risk estimator using a long short-term memory (LSTM) neural network and compare its performance to benchmark GARCH estimators. Our results indicate that even for a relatively short time series, the LSTM could be used to refine or monitor risk estimation processes and correctly identify the underlying risk dynamics in a non-parametric fashion. We evaluate the estimator on both simulated and market data with a focus on heteroscedasticity, finding that LSTM exhibits a similar performance to GARCH estimators on simulated data, whereas on real market data it is more sensitive towards increasing or decreasing volatility and outperforms all existing estimators of value-at-risk in terms of exception rate and mean quantile score.

Suggested Citation

  • Weronika Ormaniec & Marcin Pitera & Sajad Safarveisi & Thorsten Schmidt, 2022. "Estimating value at risk: LSTM vs. GARCH," Papers 2207.10539, arXiv.org.
    • Handle: RePEc:arx:papers:2207.10539
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2207.10539
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Gneiting, Tilmann, 2011. "Making and Evaluating Point Forecasts," Journal of the American Statistical Association, American Statistical Association, vol. 106(494), pages 746-762.
    2. Johanna F. Ziegel, 2016. "Coherence And Elicitability," Mathematical Finance, Wiley Blackwell, vol. 26(4), pages 901-918, October.
    3. Gurrola-Perez, Pedro & Murphy, David, 2015. "Filtered historical simulation Value-at-Risk models and their competitors," Bank of England working papers 525, Bank of England.
    4. Spyros Makridakis & Evangelos Spiliotis & Vassilios Assimakopoulos, 2018. "Statistical and Machine Learning forecasting methods: Concerns and ways forward," PLOS ONE, Public Library of Science, vol. 13(3), pages 1-26, March.
    5. Bollerslev, Tim, 1986. "Generalized autoregressive conditional heteroskedasticity," Journal of Econometrics, Elsevier, vol. 31(3), pages 307-327, April.
    6. Luc Bauwens & Sébastien Laurent & Jeroen V. K. Rombouts, 2006. "Multivariate GARCH models: a survey," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 21(1), pages 79-109, January.
    7. Rama Cont & Romain Deguest & Giacomo Scandolo, 2010. "Robustness and sensitivity analysis of risk measurement procedures," Quantitative Finance, Taylor & Francis Journals, vol. 10(6), pages 593-606.
    8. McNeil, Alexander J. & Frey, Rudiger, 2000. "Estimation of tail-related risk measures for heteroscedastic financial time series: an extreme value approach," Journal of Empirical Finance, Elsevier, vol. 7(3-4), pages 271-300, November.
    9. Engle, Robert F & Manganelli, Simone, 1999. "CAViaR: Conditional Autoregressive Value at Risk by Regression Quantiles," University of California at San Diego, Economics Working Paper Series qt06m3d6nv, Department of Economics, UC San Diego.
    10. Justin Sirignano & Rama Cont, 2019. "Universal features of price formation in financial markets: perspectives from deep learning," Quantitative Finance, Taylor & Francis Journals, vol. 19(9), pages 1449-1459, September.
    11. Hu, Yan & Ni, Jian & Wen, Liu, 2020. "A hybrid deep learning approach by integrating LSTM-ANN networks with GARCH model for copper price volatility prediction," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 557(C).
    12. Pitera, Marcin & Schmidt, Thorsten, 2018. "Unbiased estimation of risk," Journal of Banking & Finance, Elsevier, vol. 91(C), pages 133-145.
    13. Bollerslev, Tim, 1987. "A Conditionally Heteroskedastic Time Series Model for Speculative Prices and Rates of Return," The Review of Economics and Statistics, MIT Press, vol. 69(3), pages 542-547, August.
    14. Rama Cont & Romain Deguest & Giacomo Scandolo, 2010. "Robustness and sensitivity analysis of risk measurement procedures," Post-Print hal-00413729, HAL.
    15. Robert F. Engle & Simone Manganelli, 2004. "CAViaR: Conditional Autoregressive Value at Risk by Regression Quantiles," Journal of Business & Economic Statistics, American Statistical Association, vol. 22, pages 367-381, October.
    16. D Barrera & S Cr'epey & E Gobet & Hoang-Dung Nguyen & B Saadeddine, 2022. "Statistical Learning of Value-at-Risk and Expected Shortfall," Papers 2209.06476, arXiv.org, revised Sep 2024.
    17. Tobias Fissler & Johanna F. Ziegel & Tilmann Gneiting, 2015. "Expected Shortfall is jointly elicitable with Value at Risk - Implications for backtesting," Papers 1507.00244, arXiv.org, revised Jul 2015.
    18. Tobias Fissler & Jana Hlavinová & Birgit Rudloff, 2021. "Elicitability and identifiability of set-valued measures of systemic risk," Finance and Stochastics, Springer, vol. 25(1), pages 133-165, January.
    19. Trong-Nghia Nguyen & Minh-Ngoc Tran & David Gunawan & R. Kohn, 2019. "A Statistical Recurrent Stochastic Volatility Model for Stock Markets," Papers 1906.02884, arXiv.org, revised Jan 2022.
    20. Hartz, Christoph & Mittnik, Stefan & Paolella, Marc, 2006. "Accurate value-at-risk forecasting based on the normal-GARCH model," Computational Statistics & Data Analysis, Elsevier, vol. 51(4), pages 2295-2312, December.
    21. D Barrera & S Crépey & E Gobet & Hoang-Dung Nguyen & B Saadeddine, 2024. "Statistical Learning of Value-at-Risk and Expected Shortfall," Working Papers hal-03775901, HAL.
    22. Engle, Robert F, 1982. "Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation," Econometrica, Econometric Society, vol. 50(4), pages 987-1007, July.
    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. Qiu, Zhiguo & Lazar, Emese & Nakata, Keiichi, 2024. "VaR and ES forecasting via recurrent neural network-based stateful models," International Review of Financial Analysis, Elsevier, vol. 92(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. Sander Barendse & Erik Kole & Dick van Dijk, 2023. "Backtesting Value-at-Risk and Expected Shortfall in the Presence of Estimation Error," Journal of Financial Econometrics, Oxford University Press, vol. 21(2), pages 528-568.
    2. Vica Tendenan & Richard Gerlach & Chao Wang, 2020. "Tail risk forecasting using Bayesian realized EGARCH models," Papers 2008.05147, arXiv.org, revised Aug 2020.
    3. Steven Kou & Xianhua Peng, 2016. "On the Measurement of Economic Tail Risk," Operations Research, INFORMS, vol. 64(5), pages 1056-1072, October.
    4. Tim Bollerslev, 2008. "Glossary to ARCH (GARCH)," CREATES Research Papers 2008-49, Department of Economics and Business Economics, Aarhus University.
    5. Marie Kratz & Yen H Lok & Alexander J Mcneil, 2016. "Multinomial var backtests: A simple implicit approach to backtesting expected shortfall," Working Papers hal-01424279, HAL.
    6. d’Addona, Stefano & Khanom, Najrin, 2022. "Estimating tail-risk using semiparametric conditional variance with an application to meme stocks," International Review of Economics & Finance, Elsevier, vol. 82(C), pages 241-260.
    7. Kratz, Marie & Lok, Y-H & McNeil, Alexander J., 2016. "Multinomial VaR Backtests: A simple implicit approach to backtesting expected shortfall," ESSEC Working Papers WP1617, ESSEC Research Center, ESSEC Business School.
    8. Kratz, Marie & Lok, Yen H. & McNeil, Alexander J., 2018. "Multinomial VaR backtests: A simple implicit approach to backtesting expected shortfall," Journal of Banking & Finance, Elsevier, vol. 88(C), pages 393-407.
    9. Dimitriadis, Timo & Schnaitmann, Julie, 2021. "Forecast encompassing tests for the expected shortfall," International Journal of Forecasting, Elsevier, vol. 37(2), pages 604-621.
    10. Lazar, Emese & Zhang, Ning, 2019. "Model risk of expected shortfall," Journal of Banking & Finance, Elsevier, vol. 105(C), pages 74-93.
    11. Turan Bali & Panayiotis Theodossiou, 2007. "A conditional-SGT-VaR approach with alternative GARCH models," Annals of Operations Research, Springer, vol. 151(1), pages 241-267, April.
    12. Peter Christoffersen & Silvia Gonçalves, 2004. "Estimation Risk in Financial Risk Management," CIRANO Working Papers 2004s-15, CIRANO.
    13. Hoga, Yannick, 2021. "The uncertainty in extreme risk forecasts from covariate-augmented volatility models," International Journal of Forecasting, Elsevier, vol. 37(2), pages 675-686.
    14. Le, Trung H., 2020. "Forecasting value at risk and expected shortfall with mixed data sampling," International Journal of Forecasting, Elsevier, vol. 36(4), pages 1362-1379.
    15. Zhengkun Li & Minh-Ngoc Tran & Chao Wang & Richard Gerlach & Junbin Gao, 2020. "A Bayesian Long Short-Term Memory Model for Value at Risk and Expected Shortfall Joint Forecasting," Papers 2001.08374, arXiv.org, revised May 2021.
    16. Enrique Molina‐Muñoz & Andrés Mora‐Valencia & Javier Perote, 2021. "Backtesting expected shortfall for world stock index ETFs with extreme value theory and Gram–Charlier mixtures," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 26(3), pages 4163-4189, July.
    17. David Happersberger & Harald Lohre & Ingmar Nolte, 2020. "Estimating portfolio risk for tail risk protection strategies," European Financial Management, European Financial Management Association, vol. 26(4), pages 1107-1146, September.
    18. Sebastian Bayer & Timo Dimitriadis, 2022. "Regression-Based Expected Shortfall Backtesting [Backtesting Expected Shortfall]," Journal of Financial Econometrics, Oxford University Press, vol. 20(3), pages 437-471.
    19. James, Robert & Leung, Henry & Leung, Jessica Wai Yin & Prokhorov, Artem, 2023. "Forecasting tail risk measures for financial time series: An extreme value approach with covariates," Journal of Empirical Finance, Elsevier, vol. 71(C), pages 29-50.
    20. Caporale, Guglielmo Maria & Zekokh, Timur, 2019. "Modelling volatility of cryptocurrencies using Markov-Switching GARCH models," Research in International Business and Finance, Elsevier, vol. 48(C), pages 143-155.

    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:2207.10539. 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.