Home  Journals  Financial Analytics: Science and Experience  1(351) - 2020 January-March

Forecasting trends in the cryptocurrency exchange rate through the machine learning theory

Received: 26 June 2019

Received in revised form: 14 July 2019

Accepted: 2 August 2019

Available online: 28 February 2020

Subject Heading: RISK, ANALYSIS AND EVALUATION

JEL Classification: F47, F63, G17

Pages: 97–113

https://doi.org/10.24891/fa.13.1.97

Subject The study discusses methodological approaches to forecasting trends in the development of the cryptocurrency market (bitcoin).
Objectives The study aims to discover and explain tools and mechanisms for predicting how the cyptocurrency market may evolve in a short run through time series modeling methods and machine learning methods, which are based on artificial neural networks LSTM.
Methods Using Python-based programming methods, we constructed and substantiated a neural network model for the analyzable series describing how the stock exchange rate of bitcoin develops.
Results Matching loss functions, optimizer and parameters for constructing a neural network that predicts the BTC/USD exchange rate for a coming day, we proved its applicability and feasibility, which is confirmed with the lowest number of errors in the test and validation set.
Conclusions and Relevance The findings mainly prove that the above mechanism is feasible for predicting the cryptocurrency market. The mechanism is based on algorithms for constructing LSTM networks. The approach should be used to analyze and evaluate the current and future parameters of the cryptocurrency market development. The tools can be of interest for investors which operate in new markets of e-money.

Keywords: cryptocurrency market, time series, forecasting, machine learning, artificial neural networks, LSTM, Artificial Intelligence

References:

1. Safiullin M.R., El'shin L.A., Abdukaeva A.A. [Developing a stochastic model for medium-term forecasting of cryptocurrency exchange rate: The bitcoin case]. Finansy i kredit = Finance and Credit, 2018, vol. 24, iss. 5, pp. 1046–1060. (In Russ.) URL: Link
2. Luther W. Cryptocurrencies, Network Effects, and Switching Costs. Contemporary Economic Policy, 2016, vol. 34, iss. 3, pp. 553–571. URL: Link
3. Vranken H. Sustainability of Bitcoin and Blockchains. Current Opinion in Environmental Sustainability, 2017, vol. 28, pp. 1–9. URL: Link
4. White L.H. The Market for Cryptocurrencies. Cato Journal, 2015, vol. 35, no. 2, pp. 383–402. URL: Link
5. Perron P. Further Evidence on Breaking Trend Functions in Macroeconomic Variables. Journal of Econometrics, 1997, vol. 80, iss. 2, pp. 355–385. URL: Link00049-3
6. Wilson M., Yelowitz A. Characteristics of Bitcoin Users: An Analysis of Google Search Data. Applied Economics Letters, 2015, vol. 22, iss. 13, pp. 1030–1036. URL: Link
7. Raikova N.A., Yankina I.A. [Perspective use cryptocurrency as a payment instrument in Russia]. Ekonomika i predprinimatel'stvo = Journal of Economy and Entrepreneurship, 2016, no. 10-1, pp. 890–894. (In Russ.)
8. Safiullin M.R., El'shin L.A., Abdukaeva A.A. Setting the Stochastic Model for Mid-Term Prediction of Cryptocurrency Exchange Rate: The Bitcoin Case. Daidzhest-Finansy = Digest-Finance, 2018, vol. 23, iss. 3, pp. 261–273. URL: Link
9. Safiullin M.R., Abdukaeva A.A., El'shin L.A. [Development of a predictive model for the dynamics of the exchange rates of the cryptocurrencies using stochastic analysis tools]. Vestnik Instituta ekonomiki Rossiiskoi akademii nauk = Bulletin of Institute of Economics of Russian Academy of Sciences, 2018, no. 5, pp. 161–173. URL: Link (In Russ.)
10. Safiullin M.R., El'shin L.A., Abdukaeva A.A. [Development of a multi-factor predictive model for the development of a global cryptocurrency market]. Teoreticheskaya i prikladnaya ekonomika = Theoretical and Applied Economics, 2018, no. 3, pp. 151–161. (In Russ.) URL: Link
11. Kadurin A.A., Nikolenko S.I., Arkhangel'skaya E.V. Glubokoe obuchenie. Pogruzhenie v mir neironnykh setei [Deep learning. Immersion in the world of neural networks]. Saint Petersburg, Piter Publ., 2018, 480 p.
12. Strizhov V.V. [The error function in the regression recovery problems]. Zavodskaya laboratoriya = Industrial Laboratory. Diagnostics of Materials, 2013, vol. 79, no. 5, pp. 65–73. (In Russ.)
13. Rumelhart D.E., Hinton G.E., Williams R.J. Learning Representations by Back-Propagating Errors. Nature, 1986, vol. 323, pp. 533–536. URL: Link
14. Tormozov V.S. [Neural memory network research]. Uchenye zametki TOGU, 2016, vol. 7, no. 1. (In Russ.) URL: Link
15. Elman J.L. Finding Structure in Time. San Diego, University of California, 1990.
16. Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997, vol. 9, no. 8, pp. 1735–1780. URL: Link
17. Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research, 2012, vol. 13, pp. 281–305. URL: Link

View all articles of issue

ISSN 2311-8768 (Online)
ISSN 2073-4484 (Print)

Journal current issue

Vol. 17, Iss. 1 March 2024

Archive