IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2610.15296.html

Recurrent Neural Networks for Forecasting Autoregressive Noncausal Processes

Author

Listed:
  • Joann Jasiak
  • Cheng Zhong

Abstract

This paper examines the use of recurrent neural networks and their extensions for forecasting autoregressive causal-noncausal processes, characterized by local explosive patterns such as bubbles and spikes. We study the recurrent neural networks (RNN), long short-term memory networks (LSTM), gated recurrent unit (GRU), bidirectional LSTM, and also a simple feed-forward network (FNN) to reveal the difficulty of forecasting extreme values depending on the type of network and the length of the training set. We show that FNN outperforms other networks in predicting extreme values of a univariate noncausal time series during a bubble. We also examine the improvements of point predictions of extreme values resulting from pooling and a modified loss function.

Suggested Citation

  • Joann Jasiak & Cheng Zhong, 2026. "Recurrent Neural Networks for Forecasting Autoregressive Noncausal Processes," Papers 2610.15296, arXiv.org, revised Oct 2026.
    • Handle: RePEc:arx:papers:2610.15296
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2610.15296
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Parisa Foroutan & Salim Lahmiri, 2024. "Deep learning systems for forecasting the prices of crude oil and precious metals," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 10(1), pages 1-40, December.
    2. Theo Berger, 2026. "Deep Learning and Econometric Time Series Analysis: An Assessment of Daily Return Forecasts," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 45(1), pages 377-390, January.
    3. Christian Gourieroux & Andrew Hencic & Joann Jasiak, 2021. "Forecast performance and bubble analysis in noncausal MAR(1, 1) processes," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(2), pages 301-326, March.
    4. Fries, Sébastien & Zakoian, Jean-Michel, 2019. "Mixed Causal-Noncausal Ar Processes And The Modelling Of Explosive Bubbles," Econometric Theory, Cambridge University Press, vol. 35(6), pages 1234-1270, December.
    5. Lanne, Markku & Luoto, Jani & Saikkonen, Pentti, 2012. "Optimal forecasting of noncausal autoregressive time series," International Journal of Forecasting, Elsevier, vol. 28(3), pages 623-631.
    6. Christian Gourieroux & Joann Jasiak, 2016. "Filtering, Prediction and Simulation Methods for Noncausal Processes," Journal of Time Series Analysis, Wiley Blackwell, vol. 37(3), pages 405-430, May.
    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. Hecq, Alain & Issler, João Victor & Voisin, Elisa, 2024. "A short term credibility index for central banks under inflation targeting: An application to Brazil," Journal of International Money and Finance, Elsevier, vol. 143(C).
    2. Francisco Blasques & Siem Jan Koopman & Gabriele Mingoli, 2023. "Observation-Driven filters for Time- Series with Stochastic Trends and Mixed Causal Non-Causal Dynamics," Tinbergen Institute Discussion Papers 23-065/III, Tinbergen Institute, revised 01 Mar 2024.
    3. Christian Gourieroux & Andrew Hencic & Joann Jasiak, 2021. "Forecast performance and bubble analysis in noncausal MAR(1, 1) processes," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(2), pages 301-326, March.
    4. Alain Hecq & Elisa Voisin, 2023. "Predicting Crashes in Oil Prices During The Covid-19 Pandemic with Mixed Causal-Noncausal Models," Advances in Econometrics, in: Essays in Honor of Joon Y. Park: Econometric Methodology in Empirical Applications, volume 45, pages 209-233, Emerald Group Publishing Limited.
    5. Alain Hecq & Li Sun, 2019. "Identification of Noncausal Models by Quantile Autoregressions," Papers 1904.05952, arXiv.org.
    6. Hecq, Alain & Voisin, Elisa, 2021. "Forecasting bubbles with mixed causal-noncausal autoregressive models," Econometrics and Statistics, Elsevier, vol. 20(C), pages 29-45.
    7. Gabriele Mingoli, 2024. "Modeling Common Bubbles: A Mixed Causal Non-Causal Dynamic Factor Model," Tinbergen Institute Discussion Papers 24-072/III, Tinbergen Institute.
    8. Christian Gourieroux & Joann Jasiak & Michelle Tong, 2021. "Convolution‐based filtering and forecasting: An application to WTI crude oil prices," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(7), pages 1230-1244, November.
    9. Francesco Giancaterini & Alain Hecq & Joann Jasiak & Aryan Manafi Neyazi, 2025. "Regularized Generalized Covariance (RGCov) Estimator," Papers 2504.18678, arXiv.org.
    10. F. Blasques & S. J. Koopman & G. Mingoli & S. Telg, 2025. "A Novel Test for the Presence of Local Explosive Dynamics," Journal of Time Series Analysis, Wiley Blackwell, vol. 46(5), pages 966-980, September.
    11. Fries, Sébastien, 2018. "Conditional moments of noncausal alpha-stable processes and the prediction of bubble crash odds," MPRA Paper 97353, University Library of Munich, Germany, revised Nov 2019.
    12. Jian Pei & Yang Lu & Fukang Zhu, 2025. "Mixed causal-noncausal count process," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 34(2), pages 325-360, June.
    13. Yaosong Zhan & Shiqing Ling & Zhenya Liu & Shixuan Wang, 2026. "Noncausal AR‐ARCH Model and Its Applications to Financial Time Series," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 31(1), pages 1424-1443, January.
    14. Francesco Giancaterini & Alain Hecq & Joann Jasiak & Aryan Manafi Neyazi, 2025. "Bubble Detection with Application to Green Bubbles: A Noncausal Approach," Papers 2505.14911, arXiv.org, revised Apr 2026.
    15. Frédérique Bec & Heino Bohn Nielsen & Sarra Saïdi, 2020. "Mixed Causal–Noncausal Autoregressions: Bimodality Issues in Estimation and Unit Root Testing," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 82(6), pages 1413-1428, December.
    16. Telg, Sean, 2024. "Time aggregation of mixed causal–noncausal models," Economics Letters, Elsevier, vol. 244(C).
    17. Gianluca Cubadda & Alain Hecq & Sean Telg, 2019. "Detecting Co‐Movements in Non‐Causal Time Series," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 81(3), pages 697-715, June.
    18. Gourieroux, Christian & Jasiak, Joann, 2018. "Misspecification of noncausal order in autoregressive processes," Journal of Econometrics, Elsevier, vol. 205(1), pages 226-248.
    19. Tom'as del Barrio Castro & Alain Hecq & Sean Telg, 2026. "Seasonality in Mixed Causal-Noncausal Processes," Papers 2604.07040, arXiv.org.
    20. Weifeng Jin, 2023. "Quantile Autoregression-based Non-causality Testing," Papers 2301.02937, arXiv.org.

    More about this item

    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:2610.15296. 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: https://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.