financeФинансы: теория и практика/Finance: Theory and PracticeFinance: Theory and Practice2587-56712587-7089Financial University under The Government of Russian Federation10.26794/2587-5671-2022-26-4-95-108finance-1729Research ArticleЦИФРОВЫЕ ФИНАНСОВЫЕ АКТИВЫDIGITAL FINANCIAL ASSETSПрименение глубокого обучения для прогнозирования цен на криптовалюты и их взаимосвязь с адекватностью рынка (прикладное исследование на примере биткоина)Application Deep Learning to Predict Crypto Currency Prices and their Relationship to Market Adequacy (Applied Research Bitcoin as an Example)https://orcid.org/0000-0001-8295-3937АбдалхаммедМ. Х.AbdalhammedM. Kh.

Мудхер Халид Абдалхаммед - Ph.D, профессор, факультет управления и экономики

Тикрит

Moudher Kh. Abdalhammed - Ph.D., Prof., Department of Management and Economics

Tikrit

moudher@tu.edu.iqhttps://orcid.org/0000-0002-5760-3609ГазальА. М.GhazalA. M.

Ахмад Мохаммад Газаль - доцент, факультет экономики, отделение банковского дела и страхования

Дамаск

Ahmad M. Ghazal - Assistant Prof., Faculty of Economics, Department of banking andinsurance

Damascus

Ahmadghazal100@gmail.comhttps://orcid.org/0000-0001-9182-0087ИбрагимХ. М.IbrahimH. M.

Ханан Мохамед Ибрагим - магистр в области делового администрирования / финансового менеджмента, факультет делового администрирования

Тикрит

Hanan M. Ibrahim - Master’s in Business Administration/Financial Management, Faculty of Business Administration

Tikrit

Hanan.Mohamed.A@stu.edu.iqhttps://orcid.org/0000-0003-2849-026XАхмедА. Х.AhmedA. Kh.

Ахмед Худхаир Ахмед - магистр в области делового администрирования / финансового менеджмента, ассистент профессора, факультет управления и экономики, кафедра государственного управления, факультет делового администрирования

Тикрит

Ahmed Kh. Ahmed - Assistant Prof., Master’s in Business Administration/Financial Management, Faculty of Management and Economics, Department of Public Administration/Faculty of Business Administration

Tikrit

Ahmed.kh.84@tu.edu.iqТикритский университет - Колледж администрации и экономикиИракTikrit University - College of Administration and EconomicsIraqДамасский университетСирияDamascus UniversitySyrian Arab Republic20221109202226495108Copyright © Абдалхаммед М.Х., Газаль А.М., Ибрагим Х.М., Ахмед А.Х., 20222022Абдалхаммед М.Х., Газаль А.М., Ибрагим Х.М., Ахмед А.Х.Abdalhammed M.K., Ghazal A.M., Ibrahim H.M., Ahmed A.K.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://financetp.fa.ru/jour/article/view/1729

Прогнозирование курсов валют важно для всех, кто занимается трейдингом и пытается построить инвестиционный портфель из ряда криптовалют. На них не распространяются те же ограничения, что и на фиатные валюты. Цель исследования — спрогнозировать курс BITCOIN по отношению к доллару США. Краткосрочные данные (365 наблюдений) обработаны с помощью модели LSTM как одной из нейросетевых моделей. Моделирование проведено путем обучения выборки объемом 67% с учетом резких колебаний цены торгов и определенного уровня эффективности рынка. Модель GARCH использована для выбора подходящих исторических периодов для определения того, как работает модель LSTM, и для проверки эффективности на слабом, полусильном и сильном уровнях. Обработаны ряды данных, полученных с веб-сайта (Investing.com). Авторы обнаружили, что производительность нейронной сети улучшается по мере увеличения значения EPOCH при периоде обучения (исследования) в 50 дней, что согласуется с результатами проверки мастерства на слабом уровне. Это согласуется с результатами теста на достаточность на слабом уровне, что свидетельствует о том, что в исследуемом случае рынок биткоина эффективен на слабом уровне. Сделан вывод, что криптовалютным инвесторам лучше больше полагаться на исторический тренд цены валюты, чем на ее текущую цену, используя преимущества модели искусственной нейронной сети (LSTM) при работе с небольшими данными высокой волатильности.

redicting currency rates is important, for everyone who is trading and trying to build an investment portfolio from a range of crypto currencies. It is not subject to the same restrictions as fiat currencies. In this study, we seek to predict the exchange rate of BIT-COIN against the US dollar. The short-term data (365 observations) is processed using the LSTM model as one of the neural network models. Modeling is conducted by training a sample size of 67%, taking into account sharp fluctuations in the price of trade and a certain level of market efficiency. The GARCH model is used to select appropriate historical periods for how the LSTM model works and to test proficiency at the weak, semi-strong, and strong levels. The data series obtained from the website (Investing.com) have been processed. The researchers have found that the performance of the neural network improves as the EPOCH value increases with a training (research) period of 50 days before, which is consistent with the results of the proficiency test at the weak level. It agrees with the results of the sufficiency test at the weak level, which indicates that in the case under study (the Bitcoin market is effective at the weak level). It is advised that crypto-currency investors rely more on the historical trend of the price of the currency than on its current price, taking advantage of the artificial neural network model (LSTM) in dealing with little data of high volatility.

криптовалютамодель GARCHглубокое обучениеискусственные нейронные сетимодель LSTMcryptocurrencyGARCH modeldeep learningartificial neural networksLSTM modelReferencesBrownlee J. Long short-term memory networks with Python: Develop sequence prediction models with deep learning. San Juan, PR: Machine Learning Mastery; 2017. 246 p. URL: https://books.google.iq/books?hl=ar&lr=&id=m7SoDwAAQBAJ&oi=fnd&pg=PP1&dq=%5B1%5D%09Brownlee,+J.+(2017).+Long+short-term+memory+networks+with+python:+develop+sequence+prediction+models+with+deep+learning.+Machine+Learning+Mastery.+%E 2%80%8Fp.83&ots=vQIv6QdaIw&sig=Upu9DQ25Lq8TPf6x4xZi_-mTfKg&redir_esc=y#v=onepage&q&f=falseBrownlee J. Long short-term memory networks with Python: Develop sequence prediction models with deep learning. San Juan, PR: Machine Learning Mastery; 2017. 246 p. URL: https://books.google.iq/books?hl=ar&lr=&id=m7SoDwAAQBAJ&oi=fnd&pg=PP1&dq=%5B1%5D%09Brownlee,+J.+(2017).+Long+short-term+memory+networks+with+python:+develop+sequence+prediction+models+with+deep+learning.+Machine+Learning+Mastery.+%E 2%80%8Fp.83&ots=vQIv6QdaIw&sig=Upu9DQ25Lq8TPf6x4xZi_-mTfKg&redir_esc=y#v=onepage&q&f=falseGaleshchuk S., Mukherjee S. Deep networks for predicting direction of change in foreign exchange rates. Intelligent Systems in Accounting, Finance and Management. 2017;24(4):100–110. DOI: 10.1002/isaf.1404Galeshchuk S., Mukherjee S. Deep networks for predicting direction of change in foreign exchange rates. Intelligent Systems in Accounting, Finance and Management. 2017;24(4):100–110. DOI: 10.1002/isaf.1404Ionela C., Alina B. I. Eur/ron exchange rate prediction based on box-jenkins technique. SWS Journal of Social Sciences and Art. 2019;1(2):31–41. DOI: 10.35603/ssa2019/issue2.03Ionela C., Alina B. I. Eur/ron exchange rate prediction based on box-jenkins technique. SWS Journal of Social Sciences and Art. 2019;1(2):31–41. DOI: 10.35603/ssa2019/issue2.03Derbentsev V., Datsenko N., Stepanenko O., Bezkorovainyi V. Forecasting cryptocurrency prices time series using machine learning approach. SHS Web of Conferences. 2019;65:02001. DOI: 10.1051/shsconf/20196502001Derbentsev V., Datsenko N., Stepanenko O., Bezkorovainyi V. Forecasting cryptocurrency prices time series using machine learning approach. SHS Web of Conferences. 2019;65:02001. DOI: 10.1051/shsconf/20196502001Lu W., Li J., Li Y., Sun A., Wang J. A CNN-LSTM-based model to forecast stock prices. Complexity. 2020;2020:6622927. DOI: 10.1155/2020/6622927Lu W., Li J., Li Y., Sun A., Wang J. A CNN-LSTM-based model to forecast stock prices. Complexity. 2020;2020:6622927. DOI: 10.1155/2020/6622927Xue F., Sun A., Zhang H., Chng E. S. An embarrassingly simple model for dialogue relation extraction. 2020. URL: https://www.researchgate.net/publication/347966196_An_Embarrassingly_Simple_Model_for_Dialogue_Relation_ExtractionXue F., Sun A., Zhang H., Chng E. S. An embarrassingly simple model for dialogue relation extraction. 2020. URL: https://www.researchgate.net/publication/347966196_An_Embarrassingly_Simple_Model_for_Dialogue_Relation_ExtractionChaudhari A. Forecasting cryptocurrency prices using machine learning. Dublin: School of Computing, National College of Ireland; 2020. 22 p. URL: http://norma.ncirl.ie/4272/1/ashwinichaudhari.pdfChaudhari A. Forecasting cryptocurrency prices using machine learning. Dublin: School of Computing, National College of Ireland; 2020. 22 p. URL: http://norma.ncirl.ie/4272/1/ashwinichaudhari.pdfMaleki N., Nikoubin A., Rabbani M., Zeinali Y. Bitcoin price prediction based on other cryptocurrencies using machine learning and time series analysis. Scientia Iranica. 2020. DOI: 10.24200/SCI.2020.55034.4040Maleki N., Nikoubin A., Rabbani M., Zeinali Y. Bitcoin price prediction based on other cryptocurrencies using machine learning and time series analysis. Scientia Iranica. 2020. DOI: 10.24200/SCI.2020.55034.4040Derbentsev V., Babenko V., Khrustalev K., Obruch H., Khrustalova S. Comparative performance of machine learning ensemble algorithms for forecasting cryptocurrency prices. International Journal of Engineering. 2021;34(1):140–148. DOI: 10.5829/IJE.2021.34.01A.16Derbentsev V., Babenko V., Khrustalev K., Obruch H., Khrustalova S. Comparative performance of machine learning ensemble algorithms for forecasting cryptocurrency prices. International Journal of Engineering. 2021;34(1):140–148. DOI: 10.5829/IJE.2021.34.01A.16Hochreiter J. S., Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735–1780. DOI: 10.1162/neco.1997.9.8.1735Hochreiter J. S., Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735–1780. DOI: 10.1162/neco.1997.9.8.1735Yu Y., Si X., Hu C., Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation. 2019;31(7):1235–1270. DOI: 10.1162/neco_a_01199Yu Y., Si X., Hu C., Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation. 2019;31(7):1235–1270. DOI: 10.1162/neco_a_01199Cho K., Van Merriënboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proc. 2014 conf. on empirical methods in natural language processing (EMNLP). Stroudsburg, PA: Association for Computational Linguistics; 2014:1724–1734.Cho K., Van Merriënboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proc. 2014 conf. on empirical methods in natural language processing (EMNLP). Stroudsburg, PA: Association for Computational Linguistics; 2014:1724–1734.Greff K., Srivastava R. K., Koutník J., Steunebrink B. R., Schmidhuber J. LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems. 2017;28(10):2222–2232. DOI: 10.1109/TNNLS.2016.2582924Greff K., Srivastava R. K., Koutník J., Steunebrink B. R., Schmidhuber J. LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems. 2017;28(10):2222–2232. DOI: 10.1109/TNNLS.2016.2582924Jozefowicz R., Zaremba W., Sutskever I. An empirical exploration of recurrent network architectures. In: Proc. 32nd Int. conf. on machine learning (ICML’15). 2015. (Proceedings of Machine Learning Research. Vol. 37). URL: http://proceedings.mlr.press/v37/jozefowicz15.pdfJozefowicz R., Zaremba W., Sutskever I. An empirical exploration of recurrent network architectures. In: Proc. 32nd Int. conf. on machine learning (ICML’15). 2015. (Proceedings of Machine Learning Research. Vol. 37). URL: http://proceedings.mlr.press/v37/jozefowicz15.pdfGers F. A., Schmidhuber J. Recurrent nets that time and count. In: Proc. IEEE-INNS-ENNS Int. joint conf. on neural networks (IJCNN 2000). Neural computing: New challenges and perspectives for the new millennium. Piscataway, NJ: IEEE; 2000:189–194. DOI: 10.1109/IJCNN.2000.861302Gers F. A., Schmidhuber J. Recurrent nets that time and count. In: Proc. IEEE-INNS-ENNS Int. joint conf. on neural networks (IJCNN 2000). Neural computing: New challenges and perspectives for the new millennium. Piscataway, NJ: IEEE; 2000:189–194. DOI: 10.1109/IJCNN.2000.861302Van Houdt G., Mosquera C., Nápoles G. A review on the long short-term memory model. Artificial Intelligence Review. 2000;53(8):5929–5955. DOI: 10.1007/s10462–020–09838–1Van Houdt G., Mosquera C., Nápoles G. A review on the long short-term memory model. Artificial Intelligence Review. 2000;53(8):5929–5955. DOI: 10.1007/s10462–020–09838–1Shen Z., Wan Q., Leatham D. J. Bitcoin return volatility forecasting: A comparative study between GARCH and RNN. Journal of Risk and Financial Management. 2021;14(7):337. DOI: 10.3390/jrfm14070337Shen Z., Wan Q., Leatham D. J. Bitcoin return volatility forecasting: A comparative study between GARCH and RNN. Journal of Risk and Financial Management. 2021;14(7):337. DOI: 10.3390/jrfm14070337

The authors declare that there are no conflicts of interest present.