IDEAS home Printed from https://ideas.repec.org/a/gam/jrisks/v11y2023i5p79-d1130370.html
   My bibliography  Save this article

Estimating the Value-at-Risk by Temporal VAE

Author

Listed:
  • Robert Buch

    (Department of Financial Mathematics, Fraunhofer ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany)

  • Stefanie Grimm

    (Department of Financial Mathematics, Fraunhofer ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany)

  • Ralf Korn

    (Department of Mathematics, RPTU Kaiserslautern-Landau, Gottlieb-Daimler-Straße 48, 67663 Kaiserslautern, Germany)

  • Ivo Richert

    (Department of Financial Mathematics, Fraunhofer ITWM, Fraunhofer-Platz 1, 67663 Kaiserslautern, Germany)

Abstract

Estimation of the value-at-risk (VaR) of a large portfolio of assets is an important task for financial institutions. As the joint log-returns of asset prices can often be projected to a latent space of a much smaller dimension, the use of a variational autoencoder (VAE) for estimating the VaR is a natural suggestion. To ensure the bottleneck structure of autoencoders when learning sequential data, we use a temporal VAE (TempVAE) that avoids the use of an autoregressive structure for the observation variables. However, the low signal-to-noise ratio of financial data in combination with the auto-pruning property of a VAE typically makes use of a VAE prone to posterior collapse. Therefore, we use annealing of the regularization to mitigate this effect. As a result, the auto-pruning of the TempVAE works properly, which also leads to excellent estimation results for the VaR that beat classical GARCH-type, multivariate versions of GARCH and historical simulation approaches when applied to real data.

Suggested Citation

  • Robert Buch & Stefanie Grimm & Ralf Korn & Ivo Richert, 2023. "Estimating the Value-at-Risk by Temporal VAE," Risks, MDPI, vol. 11(5), pages 1-26, April.
    • Handle: RePEc:gam:jrisks:v:11:y:2023:i:5:p:79-:d:1130370
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-9091/11/5/79/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-9091/11/5/79/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Rui Luo & Weinan Zhang & Xiaojun Xu & Jun Wang, 2017. "A Neural Stochastic Volatility Model," Papers 1712.00504, arXiv.org, revised Dec 2018.
    2. Alexander Arimond & Damian Borth & Andreas Hoepner & Michael Klawunn & Stefan Weisheit, 2020. "Neural Networks and Value at Risk," Papers 2005.01686, arXiv.org, revised May 2020.
    3. Bollerslev, Tim, 1986. "Generalized autoregressive conditional heteroskedasticity," Journal of Econometrics, Elsevier, vol. 31(3), pages 307-327, April.
    4. Susan Thomas & Mandira Sarma & Ajay Shah, 2003. "Selection of Value-at-Risk models," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 22(4), pages 337-358.
    5. Laurent Laloux & Pierre Cizeau & Marc Potters & Jean-Philippe Bouchaud, 2000. "Random Matrix Theory And Financial Correlations," International Journal of Theoretical and Applied Finance (IJTAF), World Scientific Publishing Co. Pte. Ltd., vol. 3(03), pages 391-397.
    6. Xiuqin Xu & Ying Chen, 2021. "Deep Stochastic Volatility Model," Papers 2102.12658, arXiv.org.
    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. Kakade, Kshitij & Jain, Ishan & Mishra, Aswini Kumar, 2022. "Value-at-Risk forecasting: A hybrid ensemble learning GARCH-LSTM based approach," Resources Policy, Elsevier, vol. 78(C).
    2. Buczyński Mateusz & Chlebus Marcin, 2018. "Comparison of Semi-Parametric and Benchmark Value-At-Risk Models in Several Time Periods with Different Volatility Levels," Financial Internet Quarterly (formerly e-Finanse), Sciendo, vol. 14(2), pages 67-82, June.
    3. Laura Garcia‐Jorcano & Alfonso Novales, 2021. "Volatility specifications versus probability distributions in VaR forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(2), pages 189-212, March.
    4. Chrétien, Stéphane & Coggins, Frank, 2010. "Performance and conservatism of monthly FHS VaR: An international investigation," International Review of Financial Analysis, Elsevier, vol. 19(5), pages 323-333, December.
    5. McAleer, M.J. & Jiménez-Martín, J.A. & Pérez-Amaral, T., 2008. "A decision rule to minimize daily capital charges in forecasting value-at-risk," Econometric Institute Research Papers EI 2008-34, Erasmus University Rotterdam, Erasmus School of Economics (ESE), Econometric Institute.
    6. Gregory Benton & Wesley J. Maddox & Andrew Gordon Wilson, 2022. "Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes," Papers 2207.06544, arXiv.org.
    7. Qiang Zhang & Rui Luo & Yaodong Yang & Yuanyuan Liu, 2018. "Benchmarking Deep Sequential Models on Volatility Predictions for Financial Time Series," Papers 1811.03711, arXiv.org.
    8. Benjamin Beckers & Helmut Herwartz & Moritz Seidel, 2017. "Risk forecasting in (T)GARCH models with uncorrelated dependent innovations," Quantitative Finance, Taylor & Francis Journals, vol. 17(1), pages 121-137, January.
    9. Mehmet Sahiner & David G. McMillan & Dimos Kambouroudis, 2023. "Do artificial neural networks provide improved volatility forecasts: Evidence from Asian markets," Journal of Economics and Finance, Springer;Academy of Economics and Finance, vol. 47(3), pages 723-762, September.
    10. Nikita Medvedev & Zhiguang Wang, 2022. "Multistep forecast of the implied volatility surface using deep learning," Journal of Futures Markets, John Wiley & Sons, Ltd., vol. 42(4), pages 645-667, April.
    11. Cheng, Wan-Hsiu & Hung, Jui-Cheng, 2011. "Skewness and leptokurtosis in GARCH-typed VaR estimation of petroleum and metal asset returns," Journal of Empirical Finance, Elsevier, vol. 18(1), pages 160-173, January.
    12. Dimitrios P. Louzis & Spyros Xanthopoulos‐Sisinis & Apostolos P. Refenes, 2013. "The Role of High‐Frequency Intra‐daily Data, Daily Range and Implied Volatility in Multi‐period Value‐at‐Risk Forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 32(6), pages 561-576, September.
    13. Abad, Pilar & Benito, Sonia, 2013. "A detailed comparison of value at risk estimates," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 94(C), pages 258-276.
    14. Anastassios A. Drakos & Georgios P. Kouretas & Leonidas P. Zarangas, 2010. "Forecasting financial volatility of the Athens stock exchange daily returns: an application of the asymmetric normal mixture GARCH model," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 15(4), pages 331-350.
    15. Toktam Valizadeh & Saeid Rezakhah & Ferdous Mohammadi Basatini, 2021. "On time‐varying amplitude HGARCH model," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 26(2), pages 2538-2547, April.
    16. Arian, Hamid & Moghimi, Mehrdad & Tabatabaei, Ehsan & Zamani, Shiva, 2022. "Encoded Value-at-Risk: A machine learning approach for portfolio risk measurement," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 202(C), pages 500-525.
    17. Laura Garcia-Jorcano & Alfonso Novales, 2020. "A dominance approach for comparing the performance of VaR forecasting models," Computational Statistics, Springer, vol. 35(3), pages 1411-1448, September.
    18. Fredy Pokou & Jules Sadefo Kamdem & François Benhmad, 2024. "Empirical Performance of an ESG Assets Portfolio from US Market," Computational Economics, Springer;Society for Computational Economics, vol. 64(3), pages 1569-1638, September.
    19. D’Amato, Valeria & Levantesi, Susanna & Piscopo, Gabriella, 2022. "Deep learning in predicting cryptocurrency volatility," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 596(C).
    20. T. -N. Nguyen & M. -N. Tran & R. Kohn, 2020. "Recurrent Conditional Heteroskedasticity," Papers 2010.13061, arXiv.org, revised Jan 2022.

    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:gam:jrisks:v:11:y:2023:i:5:p:79-:d:1130370. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.