Skip to main content
SpringerLink
Log in

Using Machine Learning to Predict Short-Term Movements of the Bitcoin Market

  • Conference paper
  • First Online:
Enterprise Applications, Markets and Services in the Finance Industry (FinanceCom 2020)

Part of the book series: Lecture Notes in Business Information Processing ((LNBIP,volume 401))

Abstract

We analyze the predictability of the bitcoin market across prediction horizons ranging from 1 to 60 min. In doing so, we test various machine learning models and find that, while all models outperform a random classifier, recurrent neural networks and gradient boosting classifiers are especially well-suited for the examined prediction tasks. We use a comprehensive feature set, including technical, blockchain-based, sentiment-/interest-based, and asset-based features. Our results show that technical features remain most relevant for most methods, followed by selected blockchain-based and interest-based features. Additionally, we find that predictability increases for longer prediction horizons. Although a quantile-based long-short trading strategy generates monthly returns of up to 31% before transaction costs, it leads to negative returns after taking transaction costs into account due to the particularly short holding periods.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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. Nakamoto, S.: Bitcoin: a peer-to-peer electronic cash system. Working paper (2008)

    Google Scholar 

  2. Feng, G., Giglio, S., Xiu, D.: Taming the factor zoo: a test of new factors. J. Finance 75(3), 1327–1370 (2020)

    Article  Google Scholar 

  3. Jaquart, P., Dann, D., Martin, C.: Machine learning for bitcoin pricing – a structured literature review. In: Proceedings of 15th International Business Informatics Congress, pp. 174–188 (2020)

    Google Scholar 

  4. Coinmarketcap: Coinmarketcap (2020). https://coinmarketcap.com/. Accessed 30 July 2020

  5. Fama, E.F.: Efficient capital markets: a review of theory and empirical work. J. Finance 25(2), 383–417 (1970)

    Article  Google Scholar 

  6. Lo, A.W.: The adaptive markets hypothesis. J. Portf. Manag. 30(5), 15–29 (2004)

    Article  Google Scholar 

  7. Fama, E.F., French, K.R.: Dissecting anomalies. J. Finance 63(4), 1653–1678 (2008)

    Article  Google Scholar 

  8. Fischer, T., Krauss, C.: Deep learning with long short-term memory networks for financial market predictions. Eur. J. Oper. Res. 270(2), 654–669 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  9. Gu, S., Kelly, B., Xiu, D.: Empirical asset pricing via machine learning. Rev. Financ. Stud. 33(5), 2223–2273 (2020)

    Article  Google Scholar 

  10. Krollner, B., Vanstone, B., Finnie, G.: Financial time series forecasting with machine learning techniques: a survey. In: Proceedings of European Symposium on Artificial Neural Networks: Computational and Machine Learning, pp. 1–7. Springer (2010)

    Google Scholar 

  11. Fama, E.F.: Market efficiency, long-term returns, and behavioral finance. J. Financ. Econ. 49(3), 283–306 (1998)

    Article  Google Scholar 

  12. Grossman, S.J., Stiglitz, J.E.: On the impossibility of informationally efficient markets. Am. Econ. Rev. 70(3), 393–408 (1980)

    Google Scholar 

  13. Green, J., Hand, J.R.M., Zhang, X.F.: The supraview of return predictive signals. Rev. Account. Stud. 18(3), 692–730 (2013)

    Article  Google Scholar 

  14. Schwert, G.W.: Anomalies and market efficiency. In: Finantial Markets and Asset Pricing, Handbook of the Economics of Finance, pp. 939–974. Elsevier (2003)

    Google Scholar 

  15. Dyhrberg, A.H.: Bitcoin, gold and the dollar – a GARCH volatility analysis. Financ. Res. Lett. 16(1), 85–92 (2016)

    Article  Google Scholar 

  16. Burniske, C., White, A.: Bitcoin: ringing the bell for a new asset class, Technical report (2017)

    Google Scholar 

  17. Urquhart, A.: The inefficiency of Bitcoin. Econ. Lett. 148(1), 80–82 (2016)

    Article  Google Scholar 

  18. Nadarajah, S., Chu, J.: On the inefficiency of Bitcoin. Econ. Lett. 150(1), 6–9 (2017)

    Article  Google Scholar 

  19. Bariviera, A.F.: The inefficiency of Bitcoin revisited: a dynamic approach. Econ. Lett. 161(1), 1–4 (2017)

    Article  MathSciNet  Google Scholar 

  20. Vidal-Tomás, D., Ibañez, A.: Semi-strong efficiency of Bitcoin. Finance Res. Lett. 27(1), 259–265 (2018)

    Article  Google Scholar 

  21. Khuntia, S., Pattanayak, J.K.: Adaptive market hypothesis and evolving predictability of bitcoin. Econ. Lett. 167(1), 26–28 (2018)

    Article  MATH  Google Scholar 

  22. Karakoyun, E.S., Cibikdiken, A.O.: Comparison of ARIMA time series model and LSTM deep learning algorithm for bitcoin price forecasting. In: Proceedings of the Multidisciplinary Academic Conference, pp. 171–180 (2018)

    Google Scholar 

  23. McNally, S., Roche, J., Caton, S.: Predicting the price of bitcoin using machine learning. In: Proceedings of 2018 Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, pp. 339–343 (2018)

    Google Scholar 

  24. Madan, I., Saluja, S., Zhao, A.: Automated bitcoin trading via machine learning algorithms (2015)

    Google Scholar 

  25. Smuts, N.: What drives cryptocurrency prices?: an investigation of google trends and telegram sentiment. ACM SIGMETRICS Perform. Eval. Rev 46(3), 131–134 (2019)

    Article  Google Scholar 

  26. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)

    MATH  Google Scholar 

  27. Kumar, A., Garg, G.: Sentiment analysis of multimodal Twitter data. Multimed. Tools Appl. 78(17), 24103–24119 (2019)

    Article  Google Scholar 

  28. Symeonidis, S., Effrosynidis, D., Arampatzis, A.: A comparative evaluation of pre-processing techniques and their interactions for twitter sentiment analysis. Expert. Syst. Appl. 110(1), 298–310 (2018)

    Article  Google Scholar 

  29. Takeuchi, L., Lee, Y.-Y.A.: Applying deep learning to enhance momentum trading strategies in stocks (2013)

    Google Scholar 

  30. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of 3rd International Conference on Learning Representations, pp. 1–15 (2015)

    Google Scholar 

  31. Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)

    Article  MATH  Google Scholar 

  32. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  33. Chung, J., Gülçehre, Ç., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. Working Paper (2014)

    Google Scholar 

  34. Ho, T.K.: Random decision forests. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, pp. 278–282 (1995)

    Google Scholar 

  35. Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 5(21), 1189–1232 (2001)

    Article  MathSciNet  MATH  Google Scholar 

  36. Diebold, F.X., Mariano, R.S.: Comparing predictive accuracy. J. Bus. Econ. Stat. 20(1), 134–144 (1995)

    Article  MathSciNet  Google Scholar 

  37. Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)

    Article  MATH  Google Scholar 

  38. Fischer, T.G., Krauss, C., Deinert, A.: Statistical arbitrage in cryptocurrency markets. J. Risk Financ. Manag. 12(1), 31 (2019)

    Article  Google Scholar 

  39. Biais, B., Bisiere, C., Bouvard, M., Casamatta, C., Menkveld, A.J.: Equilibrium bitcoin pricing. Working Paper (2018)

    Google Scholar 

  40. Jegadeesh, N.: Evidence of predictable behavior of security returns. J. Finance 45(3), 881–898 (1990)

    Article  Google Scholar 

  41. Shefrin, H., Statman, M.: The disposition to sell winners too early and ride losers too long: theory and evidence. J. Finance 40(3), 777–790 (1985)

    Article  Google Scholar 

Download references

Acknowledgements

The authors gratefully acknowledge financial support from the ForDigital Research Alliance.

Author information

Authors and Affiliations

  1. Karlsruhe Institute for Technology, Kaiserstraße 89-93, 76133, Karlsruhe, Germany

    Patrick Jaquart, David Dann & Christof Weinhardt

Authors
  1. Patrick Jaquart
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David Dann
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Christof Weinhardt
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Patrick Jaquart .

Editor information

Editors and Affiliations

  1. Goethe University Frankfurt, Frankfurt, Germany

    Benjamin Clapham

  2. Goethe University Frankfurt, Frankfurt, Germany

    Jascha-Alexander Koch

Appendix

Appendix

1.1 A Supplemental Tables

Table 4. Probability of a true model accuracy of 50% derived from the binomial distribution described in Eq. 3.
Full size table
Table 5. Diebold-Mariano test p-values to reject the null hypothesis towards the alternative hypothesis that the forecast of model i on the test sample is more accurate than the forecast of model j.
Full size table

1.2 B Supplemental Graphical Material

See Figs. 2, 3, 4, 5, 6, 7, 8 and 9

Fig. 2.
figure 2

Feature importance of the models with memory function on the 1-min prediction horizon.

Full size image
Fig. 3.
figure 3

Feature importance of the models with memory function on the 5-min prediction horizon.

Full size image
Fig. 4.
figure 4

Feature importance of the models with memory function on the 15-min prediction horizon.

Full size image
Fig. 5.
figure 5

Feature importance of the models with memory function on the 60-min prediction horizon.

Full size image
Fig. 6.
figure 6

Feature importance of the models without memory function on the 1-min prediction horizon.

Full size image
Fig. 7.
figure 7

Feature importance of the models without memory function on the 5-min prediction horizon.

Full size image
Fig. 8.
figure 8

Feature importance of the models without memory function on the 15-min prediction horizon.

Full size image
Fig. 9.
figure 9

Feature importance of the models without memory function on the 60-min prediction horizon.

Full size image

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Jaquart, P., Dann, D., Weinhardt, C. (2020). Using Machine Learning to Predict Short-Term Movements of the Bitcoin Market. In: Clapham, B., Koch, JA. (eds) Enterprise Applications, Markets and Services in the Finance Industry. FinanceCom 2020. Lecture Notes in Business Information Processing, vol 401. Springer, Cham. https://doi.org/10.1007/978-3-030-64466-6_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-64466-6_2

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-64465-9

  • Online ISBN: 978-3-030-64466-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation