IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2203.11872.html
   My bibliography  Save this paper

Performance of long short-term memory artificial neural networks in nowcasting during the COVID-19 crisis

Author

Listed:
  • Daniel Hopp

Abstract

The COVID-19 pandemic has demonstrated the increasing need of policymakers for timely estimates of macroeconomic variables. A prior UNCTAD research paper examined the suitability of long short-term memory artificial neural networks (LSTM) for performing economic nowcasting of this nature. Here, the LSTM's performance during the COVID-19 pandemic is compared and contrasted with that of the dynamic factor model (DFM), a commonly used methodology in the field. Three separate variables, global merchandise export values and volumes and global services exports, were nowcast with actual data vintages and performance evaluated for the second, third, and fourth quarters of 2020 and the first and second quarters of 2021. In terms of both mean absolute error and root mean square error, the LSTM obtained better performance in two-thirds of variable/quarter combinations, as well as displayed more gradual forecast evolutions with more consistent narratives and smaller revisions. Additionally, a methodology to introduce interpretability to LSTMs is introduced and made available in the accompanying nowcast_lstm Python library, which is now also available in R, MATLAB, and Julia.

Suggested Citation

  • Daniel Hopp, 2022. "Performance of long short-term memory artificial neural networks in nowcasting during the COVID-19 crisis," Papers 2203.11872, arXiv.org.
    • Handle: RePEc:arx:papers:2203.11872
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2203.11872
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. World Bank, 2020. "The COVID-19 Pandemic [Pandémie De Covid-19]," World Bank Publications - Reports 33696, The World Bank Group.
    2. Huber, Florian & Koop, Gary & Onorante, Luca & Pfarrhofer, Michael & Schreiner, Josef, 2023. "Nowcasting in a pandemic using non-parametric mixed frequency VARs," Journal of Econometrics, Elsevier, vol. 232(1), pages 52-69.
    3. António José Morgado & Luis Catela Nunes & Susana Salvado, 2007. "Nowcasting an Economic Aggregate with Disaggregate Dynamic Factors: An Application to Portuguese GDP," GEE Papers 0002, Gabinete de Estratégia e Estudos, Ministério da Economia, revised Feb 2007.
    4. Foroni, Claudia & Marcellino, Massimiliano & Stevanovic, Dalibor, 2022. "Forecasting the Covid-19 recession and recovery: Lessons from the financial crisis," International Journal of Forecasting, Elsevier, vol. 38(2), pages 596-612.
    5. Cimadomo, Jacopo & Giannone, Domenico & Lenza, Michele & Monti, Francesca & Sokol, Andrej, 2022. "Nowcasting with large Bayesian vector autoregressions," Journal of Econometrics, Elsevier, vol. 231(2), pages 500-519.
    6. Brandyn Bok & Daniele Caratelli & Domenico Giannone & Argia M. Sbordone & Andrea Tambalotti, 2018. "Macroeconomic Nowcasting and Forecasting with Big Data," Annual Review of Economics, Annual Reviews, vol. 10(1), pages 615-643, August.
    7. Kuzin, Vladimir & Marcellino, Massimiliano & Schumacher, Christian, 2011. "MIDAS vs. mixed-frequency VAR: Nowcasting GDP in the euro area," International Journal of Forecasting, Elsevier, vol. 27(2), pages 529-542.
    8. Massimiliano Marcellino & Christian Schumacher, 2010. "Factor MIDAS for Nowcasting and Forecasting with Ragged‐Edge Data: A Model Comparison for German GDP," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 72(4), pages 518-550, August.
    9. Singh, Rama Krishna & Prajneshu, 2008. "Artificial Neural Network Methodology for Modelling and Forecasting Maize Crop Yield," Agricultural Economics Research Review, Agricultural Economics Research Association (India), vol. 21(1).
    10. Francisco Corona & Graciela Gonz'alez-Far'ias & Jes'us L'opez-P'erez, 2021. "A nowcasting approach to generate timely estimates of Mexican economic activity: An application to the period of COVID-19," Papers 2101.10383, arXiv.org.
    11. Kuzin, Vladimir N. & Marcellino, Massimiliano & Schumacher, Christian, 2009. "MIDAS versus mixed-frequency VAR: nowcasting GDP in the euro area," Discussion Paper Series 1: Economic Studies 2009,07, Deutsche Bundesbank.
    12. Stéphanie Guichard & Elena Rusticelli, 2011. "A Dynamic Factor Model for World Trade Growth," OECD Economics Department Working Papers 874, OECD Publishing.
    13. Daniel Hopp, 2021. "Economic Nowcasting with Long Short-Term Memory Artificial Neural Networks (LSTM)," Papers 2106.08901, arXiv.org.
    14. James Rossiter, 2010. "Nowcasting the Global Economy," Discussion Papers 10-12, Bank of Canada.
    15. Brandon Buell & Reda Cherif & Carissa Chen & Karl Walentin & Jiawen Tang & Nils Wendt, 2021. "Impact of COVID-19: Nowcasting and Big Data to Track Economic Activity in Sub-Saharan Africa," IMF Working Papers 2021/124, International Monetary Fund.
    16. Loermann, Julius & Maas, Benedikt, 2019. "Nowcasting US GDP with artificial neural networks," MPRA Paper 95459, University Library of Munich, Germany.
    17. Mark W. Watson & James H. Stock, 2004. "Combination forecasts of output growth in a seven-country data set," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 23(6), pages 405-430.
    18. Sampi Bravo,James Robert Ezequiel & Jooste,Charl, 2020. "Nowcasting Economic Activity in Times of COVID-19 : An Approximation from the Google Community Mobility Report," Policy Research Working Paper Series 9247, The World Bank.
    19. James Chapman & Ajit Desai, 2021. "Using Payments Data to Nowcast Macroeconomic Variables During the Onset of COVID-19," Staff Working Papers 21-2, Bank of Canada.
    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. Daniel Hopp, 2021. "Economic Nowcasting with Long Short-Term Memory Artificial Neural Networks (LSTM)," Papers 2106.08901, arXiv.org.
    2. Daniel Hopp, 2022. "Benchmarking Econometric and Machine Learning Methodologies in Nowcasting," Papers 2205.03318, arXiv.org.
    3. Hopp Daniel, 2022. "Economic Nowcasting with Long Short-Term Memory Artificial Neural Networks (LSTM)," Journal of Official Statistics, Sciendo, vol. 38(3), pages 847-873, September.
    4. Baumeister, Christiane & Guérin, Pierre, 2021. "A comparison of monthly global indicators for forecasting growth," International Journal of Forecasting, Elsevier, vol. 37(3), pages 1276-1295.
    5. James T. E. Chapman & Ajit Desai, 2023. "Macroeconomic Predictions Using Payments Data and Machine Learning," Forecasting, MDPI, vol. 5(4), pages 1-32, November.
    6. Longo, Luigi & Riccaboni, Massimo & Rungi, Armando, 2022. "A neural network ensemble approach for GDP forecasting," Journal of Economic Dynamics and Control, Elsevier, vol. 134(C).
    7. Danilo Cascaldi-Garcia & Matteo Luciani & Michele Modugno, 2023. "Lessons from Nowcasting GDP across the World," International Finance Discussion Papers 1385, Board of Governors of the Federal Reserve System (U.S.).
    8. Barbaglia, Luca & Frattarolo, Lorenzo & Onorante, Luca & Pericoli, Filippo Maria & Ratto, Marco & Tiozzo Pezzoli, Luca, 2023. "Testing big data in a big crisis: Nowcasting under Covid-19," International Journal of Forecasting, Elsevier, vol. 39(4), pages 1548-1563.
    9. Michael Zhemkov, 2021. "Nowcasting Russian GDP using forecast combination approach," International Economics, CEPII research center, issue 168, pages 10-24.
    10. João C. Claudio & Katja Heinisch & Oliver Holtemöller, 2020. "Nowcasting East German GDP growth: a MIDAS approach," Empirical Economics, Springer, vol. 58(1), pages 29-54, January.
    11. Dennis Kant & Andreas Pick & Jasper de Winter, 2022. "Nowcasting GDP using machine learning methods," Working Papers 754, DNB.
    12. Richard Schnorrenberger & Aishameriane Schmidt & Guilherme Valle Moura, 2024. "Harnessing Machine Learning for Real-Time Inflation Nowcasting," Working Papers 806, DNB.
    13. Katja Heinisch & Rolf Scheufele, 2018. "Bottom-up or direct? Forecasting German GDP in a data-rich environment," Empirical Economics, Springer, vol. 54(2), pages 705-745, March.
    14. Barsoum, Fady & Stankiewicz, Sandra, 2015. "Forecasting GDP growth using mixed-frequency models with switching regimes," International Journal of Forecasting, Elsevier, vol. 31(1), pages 33-50.
    15. Jansen, W. Jos & Jin, Xiaowen & de Winter, Jasper M., 2016. "Forecasting and nowcasting real GDP: Comparing statistical models and subjective forecasts," International Journal of Forecasting, Elsevier, vol. 32(2), pages 411-436.
    16. Giovanni Ballarin & Petros Dellaportas & Lyudmila Grigoryeva & Marcel Hirt & Sophie van Huellen & Juan-Pablo Ortega, 2022. "Reservoir Computing for Macroeconomic Forecasting with Mixed Frequency Data," Papers 2211.00363, arXiv.org, revised Jan 2024.
    17. Mogliani, Matteo & Simoni, Anna, 2021. "Bayesian MIDAS penalized regressions: Estimation, selection, and prediction," Journal of Econometrics, Elsevier, vol. 222(1), pages 833-860.
    18. Bańbura, Marta & Belousova, Irina & Bodnár, Katalin & Tóth, Máté Barnabás, 2023. "Nowcasting employment in the euro area," Working Paper Series 2815, European Central Bank.
    19. Bahar Şen Doğan & Murat Midiliç, 2019. "Forecasting Turkish real GDP growth in a data-rich environment," Empirical Economics, Springer, vol. 56(1), pages 367-395, January.
    20. Konstantin Kuck & Karsten Schweikert, 2021. "Forecasting Baden‐Württemberg's GDP growth: MIDAS regressions versus dynamic mixed‐frequency factor models," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(5), pages 861-882, August.

    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:2203.11872. 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.