How many neurons are needed to make a short-term prediction of the Bitcoin exchange rate?

• Autorzy: Frontczak Michał , Hachaj Tomasz

Identyfikatory

DOI

10.37705/TechTrans/e2022011

Warianty tytułu

PL

Ile neuronów jest potrzebnych, aby dokonać krótkoterminowej predykcji kursu Bitcoina?

• Języki publikacji: EN

Abstrakty

EN

The goal of our work was to select a neural network architecture that would give the best prediction of the Bitcoin exchange rate using historical data. Our work fits into the very important topic of predicting the value of the cryptocurrency exchange rate, and makes use of recent data which, as a result of the high Bitcoin exchange rate dynamics of the last year, differs significantly from those of previous years. We propose and test a number of neural network-based architectures and conduct a discussion of the results. Unlike previous state of-the-art works, we conducted a comprehensive comparison of three different neural network-based models: MLP (multilayer perceptron), LSTM (long short-term memory) and CNN (convolutional neural network). We tested them for a wide range of parameters. The results we present are, to the best of our knowledge, the most up to date when it comes to the application of artificial intelligence methods for the prediction of cryptocurrency exchange rates. The best-performing architectures were used for a website that gives real-time predictions of the Bitcoin exchange rate. The website is available at http://stpbtc-ii.up.krakow.pl/. Source codes of our research are available to download in order to make our experiment reproducible.

PL

Celem naszej pracy było stworzenie architektury sieci neuronowej, która przy wykorzystaniu danych historycznych pozwalałaby na dokładną predykcję kursu Bitcoin. Nasza praca wpisuje się w bardzo ważny temat przewidywania wartości kursu kryptowaluty. Niemniej istotny jest fakt, że w naszej pracy wykorzystujemy najnowsze dane, które z powodu dużej dynamiki kursu Bitcoin w ostatnim roku znacznie różnią się od danych z lat wcześniejszych. Proponujemy i testujemy kilka architektur opartych na sieciach neuronowych oraz przeprowadzamy dyskusję wyników. W odróżnieniu od poprzednich prac, przeprowadzamy wszechstronne porównanie trzech różnych modeli opartych na sieciach neuronowych: MLP (multilayer perceptron), LSTM (long short-term memory) i CNN (convolutional neural network). Przetestowaliśmy je dla szerokiego zakresu parametrów. Przedstawione przez nas wyniki są, według naszej wiedzy, najbardziej aktualnymi, jeśli chodzi o zastosowanie metod sztucznej inteligencji do przewidywania kursów kryptowalut. Najlepiej działająca architektura została wykorzystana na stronie internetowej, która w czasie rzeczywistym prognozuje kurs Bitcoina. Strona ta jest dostępna pod adresem http://stpbtc-ii.up.krakow.pl/. Kody źródłowe naszych badań są dostępne do pobrania w celu umożliwienia odtworzenia naszego eksperymentu.

Słowa kluczowe

EN

neural network; multiline perceptron; convolutional neural network; long short-term memory; Bitcoin

PL

sieć neuronowa; wielowarstwowy perceptron; konwolucyjna sieć neuronowa; pamięć długo-krótkotrwała; Bitcoin

• Wydawca: Wydawnictwo Politechniki Krakowskiej im. Tadeusza Kościuszki
• Czasopismo: Technical Transactions
• Rocznik: 2022
• Tom: Vol. 119, iss. 1
• Strony: art. no. e2022011
• Opis fizyczny: Bibliogr. 30 poz., tab., wykr., wz.

Twórcy

autor

Frontczak Michał

• Pedagogical University of Krakow, Institute of Computer Science

• https://orcid.org/0000-0002-5264-4508

autor

Hachaj Tomasz

• Pedagogical University of Krakow, Institute of Computer Science

• https://orcid.org/0000-0003-1390-9021

Bibliografia

• 1. Dutta, A., Kumar, S., Basu, M. (2020). A Gated Recurrent Unit Approach to Bitcoin Price Prediction. J. Risk Financial Manag., 13, 23. https://doi.org/10.3390/jrfm13020023
• 2. Ferdiansyah, F., Othman, S.H., Zahilah Raja R., Md, Radzi, Stiawan, D., Sazaki, Y., Ependi, U. (2019). A LSTM-Method for Bitcoin Price Prediction: A Case Study Yahoo Finance Stock Market, International Conference on Electrical Engineering and Computer Science (ICECOS), 206–210, https://doi.org/10.1109/ICECOS47637.2019.8984499
• 3. Ho, K.-H., Chan, T.-T., Pan, H., Li, C. (2021). Do Candlestick Patterns Work in Cryptocurrency Trading?, IEEE International Conference on Big Data, 4566–4569, https://doi.org/10.1109/BigData52589.2021.9671826
• 4. Huang, Y., Capretz, L. F., Ho, D. (2021). Machine Learning for Stock Prediction Based on Fundamental Analysis. IEEE Symposium Series on Computational Intelligence (SSCI), 01–10, https://doi.org/10.1109/SSCI50451.2021.9660134
• 5. Huang X. et al. (2021). LSTM Based Sentiment Analysis for Cryptocurrency Prediction. In: Database Systems for Advanced Applications, ed. C.S. Jensen. Lecture Notes in Computer Science, vol. 12683. Springer, Cham. https://doi.org/10.1007/978-3-030-73200-4_
• 6. Hu, Z., Liu, W., Bian, J., Liu, X., Tie-Yan, L. (2018). Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining (WSDM‘18). New York: Association for Computing Machinery, 261–269. https://doi.org/10.1145/3159652.3159690
• 7. Hyndman, R.J., Koehler, A.B. (2006). Another look at measures of forecast accuracy, International Journal of Forecasting, Vol. 22, Issue 4, 679–688, https://doi.org/10.1016/j.ijforecast.2006.03.001
• 8. Inzirillo, H., Benjamin, M. (2021). Dimensionality reduction for prediction: Application to Bitcoin and Ethereum, arXiv: 2112.15036
• 9. Ji, S., Kim, J., Im, H.A. (2019). Comparative Study of Bitcoin Price Prediction Using Deep Learning. Mathematics, 7, 898. https://doi.org/10.3390/math7100898
• 10. Kingma, D., Ba, J. (2014). A Method for Stochastic Optimization. International Conference on Learning Representations.
• 11. Li, T.R., Chamrajnagar, A.S., Fong, X.R., Rizik, N.R. Fu, F. (2019). Sentiment-Based Prediction of Alternative Cryptocurrency Price Fluctuations Using Gradient Boosting Tree Model. Front. Phys., 7: 98. https://doi.org/10.3389/fphy.2019.00098
• 12. Liu, F., Li, Y., Li, B., Li, J., Xie, H. (2021). Bitcoin transaction strategy construction based on deep reinforcement learning. Applied Soft Computing, 113, 107952. 10.1016/j.asoc.2021.107952.
• 13. Mangla, N., Bhat, A., Avabratha, G., Narayana Bhat (2019). Bitcoin Price Prediction Using Machine Learning, International Journal of Information and Computing Science.
• 14. Matic, J.L., Packham, N., Härdle, W.K. (2021). Hedging Cryptocurrency Options. Retrieved from: https://ssrn.com/abstract=3968594 or http://dx.doi.org/10.2139/ssrn.3968594 [online: 1.03.2022].
• 15. Mezquita Y., Gil-González A.B., Prieto J., Corchado J.M. (2022). Cryptocurrencies and Price Prediction: A Survey. In: Blockchain and Applications, eds. J. Prieto, A. Partida, P. Leitão, A. Pinto. Lecture Notes in Networks and Systems, Vol. 320. Springer, Cham. https://doi.org/10.1007/978-3-030-86162-9
• 16. Mittal, A., Dhiman, V., Singh, A., Prakash C. (2019). Short-Term Bitcoin Price Fluctuation Prediction Using Social Media and Web Search Data, 12th International Conference on Contemporary Computing (IC3), 1–6, https://doi.org/10.1109/IC3.2019.8844899
• 17. Nakamoto, S. (2009). Bitcoin: A Peer-to-Peer Electronic Cash System, Cryptography Mailing. Retrieved from: https://metzdowd.com [online: 1.03.2022].
• 18. Nazário, R.T.F., Lima e Silva, J., Sobreiro, V.A., Kimura, H. (2017). A literaturę review of technical analysis on stock markets. The Quarterly Review of Economics and Finance, Vol. 66: 115–126. https://doi.org/10.1016/j.qref.2017.01.014.
• 19. Number of cryptocurrencies worldwide from 2013 to February 2022 (2022). Retrieved from: https://www.statista.com/statistics/863917/number-crypto-coins-tokens [online: 1.03.2022].
• 20. Patel, J., Kalariya, V., Parmar, P., Tanwar, S., Kumar, N., Alazab, M. (2020). Stochastic Neural Networks For Cryptocurrency Price Prediction. IEEE Access. https://doi.org/10.1109/ACCESS.2020.2990659
• 21. Phaladisailoed, T., Numnonda, T. (2018). Machine Learning Models Comparison for Bitcoin Price Prediction, 10th International Conference on Information Technology and Electrical Engineering (ICITEE), 506–511, https://doi.org/10.1109/ICITEED.2018.8534911
• 22. Rane, P.V., Dhage, S.N. (2019). Systematic Erudition of Bitcoin Price Prediction using Machine Learning Techniques, 5 th International Conference on Advanced Computing & Communication Systems (ICACCS), 594–598, https://doi.org/10.1109/ICACCS.2019.8728424
• 23. Rizwan, M., Narejo, S. Javed, M. (2019). Bitcoin price prediction using Deep Learning Algorithm, 13th International Conference on Mathematics, Actuarial Science, Computer Science and Statistics (MACS), 1–7, https://doi.org/10.1109/MACS48846.2019.9024772
• 24. Sen, J., Dutta, A., Mehtab, S., (2021). Stock Portfolio Optimization Using a Deep Learning LSTM Model, arXiv.org:2111.04709.
• 25. Struga, K., Olti Q. (2018). Bitcoin Price Prediction with Neural Networks, RTA-CSIT.
• 26. Taylor, S.J., Letham, B. (2017). Forecasting at scale. Peer J. Preprints 5:e3190v2, https://doi.org/10.7287/peerj.preprints.3190v2
• 27. Top Cryptocurrency Spot Exchanges. Retrieved from: https://coinmarketcap.com/rankings/exchanges [online: 1.03.2022]. All Cryptocurrencies. Retrieved from: https://coinmarketcap.com/all/views/all [online: 1.03.2022].
• 28. Tsai, Y., Chen, J., Wang, J. (2020). Predict Forex Trend via Convolutional Neural Networks. Journal of Intelligent Systems, 29, 941– 958.
• 29. Wołk, K. (2020). Advanced social media sentiment analysis for short-term cryptocurrency price prediction. Expert Systems. 37:e12493. https://doi.org/10.1111/exsy.12493
• 30. Zhao, D., Rinaldo, A., Brookins, C. (2019). Cryptocurrency Price Prediction and Trading Strategies Using Support Vector Machines, arXiv:1911.11819.

Uwagi

Section "Computer Sciences"