Skip to main content
SpringerLink
Log in

Forecasting Cryptocurrency Prices Using Contextual ES-adRNN with Exogenous Variables

  • Conference paper
  • First Online:
Computational Science – ICCS 2023 (ICCS 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14073))

Included in the following conference series:

Abstract

In this paper, we introduce a new approach to multivariate forecasting cryptocurrency prices using a hybrid contextual model combining exponential smoothing (ES) and recurrent neural network (RNN). The model consists of two tracks: the context track and the main track. The context track provides additional information to the main track, extracted from representative series. This information as well as information extracted from exogenous variables is dynamically adjusted to the individual series forecasted by the main track. The RNN stacked architecture with hierarchical dilations, incorporating recently developed attentive dilated recurrent cells, allows the model to capture short and long-term dependencies across time series and dynamically weight input information. The model generates both point daily forecasts and predictive intervals for one-day, one-week and four-week horizons. We apply our model to forecast prices of 15 cryptocurrencies based on 17 input variables and compare its performance with that of comparative models, including both statistical and ML ones.

G.D. thanks prof. W.K. Härdle for his guidance on cryptocurrencies. G.D. and P.P. were partially supported by grant 020/RID/2018/19 “Regional Initiative of Excellence” from the Polish Minister of Science and Higher Education, 2019–23.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Giudici, G., Milne, A., Vinogradov, D.: Cryptocurrencies: market analysis and perspectives. J. Ind. Bus. Econ. 47, 1–18 (2020)

    Article  Google Scholar 

  2. Sovbetov, Y.: Factors influencing cryptocurrency prices: evidence from bitcoin, ethereum, dash, litcoin, and monero. J. Econ. Finan. Anal. 2, 1–27 (2018)

    Google Scholar 

  3. Walther, T., Klein, T., Bouri, E.: Exogenous drivers of Bitcoin and Cryptocurrency volatility–a mixed data sampling approach to forecasting. J. Int. Finan. Markets. Inst. Money 63, 101133 (2019)

    Article  Google Scholar 

  4. Gradojevic, N., Kukolj, D., Adcock, R., Djakovic, V.: Forecasting Bitcoin with technical analysis: a not-so-random forest? Int. J. Forecast. 39, 1–17 (2023)

    Article  Google Scholar 

  5. Mudassir, M., Bennbaia, S., Unal, D., Hammoudeh, M.: Time-series forecasting of Bitcoin prices using high-dimensional features: a machine learning approach. Neural Comput. Appl. (2020). https://doi.org/10.1007/s00521-020-05129-6

  6. Ahmed, W.M.: Robust drivers of Bitcoin price movements: an extreme bounds analysis. North Am. J. Econ. Finan. 62, 101728 (2022)

    Article  Google Scholar 

  7. Kraaijeveld, O., De Smedt, J.: The predictive power of public Twitter sentiment for forecasting cryptocurrency prices. J. Int. Finan. Markets. Inst. Money 65, 101188 (2020)

    Article  Google Scholar 

  8. Bouri, E., Lau, C.K.M., Lucey, B., Roubaud, D.: Trading volume and the predictability of return and volatility in the cryptocurrency market. Financ. Res. Lett. 29, 340–346 (2019)

    Article  Google Scholar 

  9. Saad, M., et al.: Toward characterizing blockchain-based cryptocurrencies for highly accurate predictions. IEEE Syst. J. 14, 321–332 (2019)

    Article  Google Scholar 

  10. Khedr, A.M., et al.: Cryptocurrency price prediction using traditional statistical and machine-learning techniques: a survey. Intell. Syst. Account. Finan. Manag. 28, 3–34 (2021)

    Article  Google Scholar 

  11. Hotz-Behofsits, C., Huber, F., Zörner, T.O.: Predicting crypto-currencies using sparse non-Gaussian state space models. J. Forecast. 37, 627–640 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  12. Giudici, P., Abu-Hashish, I.: What determines bitcoin exchange prices? A network VAR approach. Financ. Res. Lett. 28, 309–318 (2019)

    Article  Google Scholar 

  13. Kim, G., Shin, D.-H., Choi, J.G., Lim, S.: A deep learning-based Cryptocurrency price prediction model that uses on-chain data. IEEE Access 10, 56232–56248 (2022)

    Article  Google Scholar 

  14. Hansun, S., Wicaksana, A., Khaliq, A.Q.: Multivariate cryptocurrency prediction: comparative analysis of three recurrent neural networks approaches. J. Big Data 9, 1–15 (2022)

    Article  Google Scholar 

  15. Chen, J.: Analysis of Bitcoin price prediction using machine learning. J. Risk Finan. Manag. 16, 51 (2023)

    Article  Google Scholar 

  16. Chen, Z., Li, C., Sun, W.: Bitcoin price prediction using machine learning: an approach to sample dimension engineering. J. Comput. Appl. Math. 365, 112395 (2020)

    Article  MathSciNet  MATH  Google Scholar 

  17. Smyl, S., Dudek, G., Pełka, P.: Contextually enhanced ES-dRNN with dynamic attention for short-term load forecasting. arXiv preprint arXiv:2212.09030 (2022)

  18. Smyl, S., Dudek, G., Pelka, P.: ES-dRNN with dynamic attention for short-term load forecasting. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2022)

    Google Scholar 

  19. Smyl, S., Dudek, G., Pełka, P.: ES-dRNN: a hybrid exponential smoothing and dilated recurrent neural network model for short-term load forecasting. arXiv preprint arXiv:2112.02663 (2021)

  20. Smyl, S.: A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. Int. J. Forecast. 36, 75–85 (2020)

    Article  Google Scholar 

  21. Dudek, G., Pełka, P., Smyl, S.: A hybrid residual dilated LSTM and exponential smoothing model for midterm electric load forecasting. IEEE Trans. Neural Netw. Learn. Syst. 33, 2879–2891 (2021)

    Article  Google Scholar 

  22. Dudek, G.: Pattern similarity-based methods for short-term load forecasting-Part 2: models. Appl. Soft Comput. 36, 422–441 (2015)

    Article  Google Scholar 

  23. Dudek, G.: Neural networks for pattern-based short-term load forecasting: a comparative study. Neurocomputing 205, 64–74 (2016)

    Article  Google Scholar 

  24. Salinas, D., Flunkert, V., Gasthaus, J., Januschowski, T.: DeepAR: probabilistic forecasting with autoregressive recurrent networks. Int. J. Forecast. 36, 1181–1191 (2020)

    Article  Google Scholar 

  25. Oreshkin, B.N., Carpov, D., Chapados, N., Bengio, Y.: N-BEATS: neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437 (2019)

  26. Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  27. Oord, A., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)

  28. Alexandrov, A., et al.: Gluonts: probabilistic and neural time series modeling in python. J. Mach. Learn. Res. 21, 4629–4634 (2020)

    Google Scholar 

  29. Giacomini, R., White, H.: Tests of conditional predictive ability. Econometrica 74(6), 1545–1578 (2006)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Częstochowa, Poland

    Slawek Smyl

  2. Electrical Engineering Faculty, Czestochowa University of Technology, Częstochowa, Poland

    Grzegorz Dudek & Paweł Pełka

Authors
  1. Slawek Smyl
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Grzegorz Dudek
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Paweł Pełka
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Grzegorz Dudek .

Editor information

Editors and Affiliations

  1. Czech Technical University in Prague, Prague, Czech Republic

    Jiří Mikyška

  2. University of Amsterdam, Amsterdam, The Netherlands

    Clélia de Mulatier

  3. AGH University of Science and Technology, Krakow, Poland

    Maciej Paszynski

  4. University of Amsterdam, Amsterdam, The Netherlands

    Valeria V. Krzhizhanovskaya

  5. University of Tennessee at Knoxville, Knoxville, TN, USA

    Jack J. Dongarra

  6. University of Amsterdam, Amsterdam, The Netherlands

    Peter M.A. Sloot

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Smyl, S., Dudek, G., Pełka, P. (2023). Forecasting Cryptocurrency Prices Using Contextual ES-adRNN with Exogenous Variables. In: Mikyška, J., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2023. ICCS 2023. Lecture Notes in Computer Science, vol 14073. Springer, Cham. https://doi.org/10.1007/978-3-031-35995-8_32

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-35995-8_32

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-35994-1

  • Online ISBN: 978-3-031-35995-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation