IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2508.18921.html

Forecasting Probability Distributions of Financial Returns with Deep Neural Networks

Author

Listed:
  • Jakub Micha'nk'ow

Abstract

This study evaluates deep neural networks for forecasting probability distributions of financial returns. 1D convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) architectures are used to forecast parameters of three probability distributions: Normal, Student's t, and skewed Student's t. Using custom negative log-likelihood loss functions, distribution parameters are optimized directly. The models are tested on six major equity indices (S\&P 500, BOVESPA, DAX, WIG, Nikkei 225, and KOSPI) using probabilistic evaluation metrics including Log Predictive Score (LPS), Continuous Ranked Probability Score (CRPS), and Probability Integral Transform (PIT). Results show that deep learning models provide accurate distributional forecasts and perform competitively with classical GARCH models for Value-at-Risk estimation. The LSTM with skewed Student's t distribution performs best across multiple evaluation criteria, capturing both heavy tails and asymmetry in financial returns. This work shows that deep neural networks are viable alternatives to traditional econometric models for financial risk assessment and portfolio management.

Suggested Citation

  • Jakub Micha'nk'ow, 2025. "Forecasting Probability Distributions of Financial Returns with Deep Neural Networks," Papers 2508.18921, arXiv.org, revised Aug 2025.
  • Handle: RePEc:arx:papers:2508.18921
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2508.18921
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Patton, Andrew J. & Ziegel, Johanna F. & Chen, Rui, 2019. "Dynamic semiparametric models for expected shortfall (and Value-at-Risk)," Journal of Econometrics, Elsevier, vol. 211(2), pages 388-413.
    2. Anne Opschoor & Dick van Dijk & Michel van der Wel, 2017. "Combining density forecasts using focused scoring rules," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 32(7), pages 1298-1313, November.
    3. Salinas, David & Flunkert, Valentin & Gasthaus, Jan & Januschowski, Tim, 2020. "DeepAR: Probabilistic forecasting with autoregressive recurrent networks," International Journal of Forecasting, Elsevier, vol. 36(3), pages 1181-1191.
    4. Marcjasz, Grzegorz & Narajewski, Michał & Weron, Rafał & Ziel, Florian, 2023. "Distributional neural networks for electricity price forecasting," Energy Economics, Elsevier, vol. 125(C).
    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. Trottier, Denis-Alexandre & Ardia, David, 2016. "Moments of standardized Fernandez–Steel skewed distributions: Applications to the estimation of GARCH-type models," Finance Research Letters, Elsevier, vol. 18(C), pages 311-316.
    7. Jieyu Chen & Sebastian Lerch & Melanie Schienle & Tomasz Serafin & Rafal Weron, 2025. "Probabilistic intraday electricity price forecasting using generative machine learning," WORking papers in Management Science (WORMS) WORMS/25/05, Department of Operations Research and Business Intelligence, Wroclaw University of Science and Technology.
    8. Stephen Thiele, 2020. "Modeling the conditional distribution of financial returns with asymmetric tails," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 35(1), pages 46-60, January.
    9. 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.
    10. Georg Keilbar & Weining Wang, 2022. "Modelling systemic risk using neural network quantile regression," Empirical Economics, Springer, vol. 62(1), pages 93-118, January.
    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. Wang, Shuai & Wang, Qian & Lu, Helen & Zhang, Dongxue & Xing, Qianyi & Wang, Jianzhou, 2025. "Learning about tail risk: Machine learning and combination with regularization in market risk management," Omega, Elsevier, vol. 133(C).
    2. Catania, Leopoldo & Grassi, Stefano, 2022. "Forecasting cryptocurrency volatility," International Journal of Forecasting, Elsevier, vol. 38(3), pages 878-894.
    3. Taylor, James W., 2020. "Forecast combinations for value at risk and expected shortfall," International Journal of Forecasting, Elsevier, vol. 36(2), pages 428-441.
    4. Ardia, David & Bluteau, Keven & Boudt, Kris & Catania, Leopoldo, 2018. "Forecasting risk with Markov-switching GARCH models:A large-scale performance study," International Journal of Forecasting, Elsevier, vol. 34(4), pages 733-747.
    5. Federico Gatta & Fabrizio Lillo & Piero Mazzarisi, 2024. "CAESar: Conditional Autoregressive Expected Shortfall," Papers 2407.06619, arXiv.org.
    6. Fritzsch, Simon & Timphus, Maike & Weiß, Gregor, 2024. "Marginals versus copulas: Which account for more model risk in multivariate risk forecasting?," Journal of Banking & Finance, Elsevier, vol. 158(C).
    7. Taylor, James W., 2022. "Forecasting Value at Risk and expected shortfall using a model with a dynamic omega ratio," Journal of Banking & Finance, Elsevier, vol. 140(C).
    8. Agakishiev, Ilyas & Härdle, Wolfgang Karl & Kopa, Milos & Kozmik, Karel & Petukhina, Alla, 2025. "Multivariate probabilistic forecasting of electricity prices with trading applications," Energy Economics, Elsevier, vol. 141(C).
    9. Hanus, Luboš & Baruník, Jozef, 2025. "Learning the probability distributions of day-ahead electricity prices," Energy Economics, Elsevier, vol. 152(C).
    10. Qifa Xu & Lu Chen & Cuixia Jiang & Yezheng Liu, 2022. "Forecasting expected shortfall and value at risk with a joint elicitable mixed data sampling model," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 41(3), pages 407-421, April.
    11. Jonathan Berrisch & Florian Ziel, 2023. "Multivariate Probabilistic CRPS Learning with an Application to Day-Ahead Electricity Prices," Papers 2303.10019, arXiv.org, revised Feb 2024.
    12. Simon Hirsch, 2025. "Online Multivariate Regularized Distributional Regression for High-dimensional Probabilistic Electricity Price Forecasting," Papers 2504.02518, arXiv.org, revised Oct 2025.
    13. Gerlach, Richard & Wang, Chao, 2020. "Semi-parametric dynamic asymmetric Laplace models for tail risk forecasting, incorporating realized measures," International Journal of Forecasting, Elsevier, vol. 36(2), pages 489-506.
    14. Timo Dimitriadis & iaochun Liu & Julie Schnaitmann, 2023. "Encompassing Tests for Value at Risk and Expected Shortfall Multistep Forecasts Based on Inference on the Boundary," Journal of Financial Econometrics, Oxford University Press, vol. 21(2), pages 412-444.
    15. Li, Li & Kang, Yanfei & Li, Feng, 2023. "Bayesian forecast combination using time-varying features," International Journal of Forecasting, Elsevier, vol. 39(3), pages 1287-1302.
    16. Wang, Shengjie & Kang, Yanfei & Petropoulos, Fotios, 2024. "Combining probabilistic forecasts of intermittent demand," European Journal of Operational Research, Elsevier, vol. 315(3), pages 1038-1048.
    17. Leandro Maciel, 2021. "Cryptocurrencies value‐at‐risk and expected shortfall: Do regime‐switching volatility models improve forecasting?," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 26(3), pages 4840-4855, July.
    18. Hauzenberger, Niko & Pfarrhofer, Michael & Rossini, Luca, 2025. "Sparse time-varying parameter VECMs with an application to modeling electricity prices," International Journal of Forecasting, Elsevier, vol. 41(1), pages 361-376.
    19. Gael M. Martin & David T. Frazier & Ruben Loaiza-Maya & Florian Huber & Gary Koop & John Maheu & Didier Nibbering & Anastasios Panagiotelis, 2023. "Bayesian Forecasting in the 21st Century: A Modern Review," Monash Econometrics and Business Statistics Working Papers 1/23, Monash University, Department of Econometrics and Business Statistics.
    20. Santos, Douglas G. & Candido, Osvaldo & Tófoli, Paula V., 2022. "Forecasting risk measures using intraday and overnight information," The North American Journal of Economics and Finance, Elsevier, vol. 60(C).

    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:2508.18921. 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.