IDEAS home Printed from https://ideas.repec.org/a/nbp/nbpbik/v52y2021i5p457-472.html
   My bibliography  Save this article

Prognozowanie indeksu WIG20 za pomocą sieci neuronowych NARX i metody SVM

Author

Listed:
  • Sylwia Radomska

    (Uniwersytet Warszawski, Wydział Zarządzania; FAME|GRAPE)

Abstract

elem artykułu jest porównanie błędu prognoz indeksu WIG20 uzyskanych za pomocą tradycyjnej metody statystycznej oraz metod uczenia maszynowego: metody wektorów nośnych i metamodelu opartego na sieciach neuronowych NARX. Przeprowadzona analiza wskazuje, że metoda SVM pozwoliła na uzyskanie prognoz o największej precyzji (najniższych wartościach błędów ex post). Obie metody uczenia maszynowego cechowały się istotnie większą dokładnością prognoz w porównaniu z zastosowaną metodą statystyczną w okresie styczeń 2017 – marzec 2018 r. Tradycyjne modele statystyczne wymagają szeregu założeń dotyczących zależności pomiędzy zmiennymi, szeroko krytykowanych w literaturze za arbitralność. Charakterystyka modeli uczenia maszynowego z jednej strony podkreśla ich zdolność do wykrywania złożonych i nieliniowych zależności w danych historycznych, ale z drugiej strony wskazuje na ich inne ograniczenia metodologiczne.

Suggested Citation

  • Sylwia Radomska, 2021. "Prognozowanie indeksu WIG20 za pomocą sieci neuronowych NARX i metody SVM," Bank i Kredyt, Narodowy Bank Polski, vol. 52(5), pages 457-472.
    • Handle: RePEc:nbp:nbpbik:v:52:y:2021:i:5:p:457-472
    as

    Download full text from publisher

    File URL: https://bankikredyt.nbp.pl/content/2021/05/bik_05_2021_03.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Diebold, Francis X & Mariano, Roberto S, 2002. "Comparing Predictive Accuracy," Journal of Business & Economic Statistics, American Statistical Association, vol. 20(1), pages 134-144, January.
    2. Tamal Datta Chaudhuri & Indranil Ghosh, 2016. "Artificial Neural Network and Time Series Modeling Based Approach to Forecasting the Exchange Rate in a Multivariate Framework," Papers 1607.02093, arXiv.org.
    3. Zina Boussaada & Octavian Curea & Ahmed Remaci & Haritza Camblong & Najiba Mrabet Bellaaj, 2018. "A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation," Energies, MDPI, vol. 11(3), pages 1-21, March.
    4. Tay, Francis E. H. & Cao, Lijuan, 2001. "Application of support vector machines in financial time series forecasting," Omega, Elsevier, vol. 29(4), pages 309-317, August.
    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. Heni Boubaker & Giorgio Canarella & Rangan Gupta & Stephen M. Miller, 2023. "A Hybrid ARFIMA Wavelet Artificial Neural Network Model for DJIA Index Forecasting," Computational Economics, Springer;Society for Computational Economics, vol. 62(4), pages 1801-1843, December.
    2. Tang, Ling & Yu, Lean & Wang, Shuai & Li, Jianping & Wang, Shouyang, 2012. "A novel hybrid ensemble learning paradigm for nuclear energy consumption forecasting," Applied Energy, Elsevier, vol. 93(C), pages 432-443.
    3. Oscar Claveria & Enric Monte & Salvador Torra, 2016. "Modelling cross-dependencies between Spain’s regional tourism markets with an extension of the Gaussian process regression model," SERIEs: Journal of the Spanish Economic Association, Springer;Spanish Economic Association, vol. 7(3), pages 341-357, August.
    4. Viviana Fernandez, 2008. "Traditional versus novel forecasting techniques: how much do we gain?," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 27(7), pages 637-648.
    5. Flavio Barboza & Geraldo Nunes Silva & José Augusto Fiorucci, 2023. "A review of artificial intelligence quality in forecasting asset prices," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 42(7), pages 1708-1728, November.
    6. Lee, Juyong & Cho, Youngsang, 2022. "National-scale electricity peak load forecasting: Traditional, machine learning, or hybrid model?," Energy, Elsevier, vol. 239(PD).
    7. Theodore Syriopoulos & Michael Tsatsaronis & Ioannis Karamanos, 2021. "Support Vector Machine Algorithms: An Application to Ship Price Forecasting," Computational Economics, Springer;Society for Computational Economics, vol. 57(1), pages 55-87, January.
    8. Wang, Shuai & Yu, Lean & Tang, Ling & Wang, Shouyang, 2011. "A novel seasonal decomposition based least squares support vector regression ensemble learning approach for hydropower consumption forecasting in China," Energy, Elsevier, vol. 36(11), pages 6542-6554.
    9. Viviana Fernández, 2006. "Forecasting crude oil and natural gas spot prices by classification methods," Documentos de Trabajo 229, Centro de Economía Aplicada, Universidad de Chile.
    10. Bangzhu Zhu & Shunxin Ye & Ping Wang & Julien Chevallier & Yi‐Ming Wei, 2022. "Forecasting carbon price using a multi‐objective least squares support vector machine with mixture kernels," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 41(1), pages 100-117, January.
    11. Kyoung-jae Kim & Kichun Lee & Hyunchul Ahn, 2018. "Predicting Corporate Financial Sustainability Using Novel Business Analytics," Sustainability, MDPI, vol. 11(1), pages 1-17, December.
    12. Arnerić Josip & Poklepović Tea & Teai Juin Wen, 2018. "Neural Network Approach in Forecasting Realized Variance Using High-Frequency Data," Business Systems Research, Sciendo, vol. 9(2), pages 18-34, July.
    13. Charalampos Stasinakis & Georgios Sermpinis & Ioannis Psaradellis & Thanos Verousis, 2016. "Krill-Herd Support Vector Regression and heterogeneous autoregressive leverage: evidence from forecasting and trading commodities," Quantitative Finance, Taylor & Francis Journals, vol. 16(12), pages 1901-1915, December.
    14. Ling‐Jing Kao & Chih‐Chou Chiu & Hung‐Jui Wang & Chang Yu Ko, 2021. "Prediction of remaining time on site for e‐commerce users: A SOM and long short‐term memory study," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(7), pages 1274-1290, November.
    15. Tea Šestanović & Josip Arnerić, 2021. "Neural network structure identification in inflation forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(1), pages 62-79, January.
    16. Jichang Dong & Wei Dai & Ying Liu & Lean Yu & Jie Wang, 2019. "Forecasting Chinese Stock Market Prices using Baidu Search Index with a Learning-Based Data Collection Method," International Journal of Information Technology & Decision Making (IJITDM), World Scientific Publishing Co. Pte. Ltd., vol. 18(05), pages 1605-1629, September.
    17. Fernandez, Viviana, 2007. "Wavelet- and SVM-based forecasts: An analysis of the U.S. metal and materials manufacturing industry," Resources Policy, Elsevier, vol. 32(1-2), pages 80-89.
    18. Anatoly A. Peresetsky & Ruslan I. Yakubov, 2017. "Autocorrelation in an unobservable global trend: does it help to forecast market returns?," International Journal of Computational Economics and Econometrics, Inderscience Enterprises Ltd, vol. 7(1/2), pages 152-169.
    19. Kelly Burns & Imad Moosa, 2017. "Demystifying the Meese–Rogoff puzzle: structural breaks or measures of forecasting accuracy?," Applied Economics, Taylor & Francis Journals, vol. 49(48), pages 4897-4910, October.
    20. 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.

    More about this item

    Keywords

    prognozowanie; WIG20; sieci neuronowe (NARX); metoda wektorów nośnych (SVM); efektywność rynku;
    All these keywords.

    JEL classification:

    • G17 - Financial Economics - - General Financial Markets - - - Financial Forecasting and Simulation
    • G14 - Financial Economics - - General Financial Markets - - - Information and Market Efficiency; Event Studies; Insider Trading
    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
    • C53 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Forecasting and Prediction Models; Simulation Methods

    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:nbp:nbpbik:v:52:y:2021:i:5:p:457-472. 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: Wojciech Burjanek (email available below). General contact details of provider: https://edirc.repec.org/data/nbpgvpl.html .

    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.