PROBLEM ANALYSIS OF FORECASTING CRYPTOCURRENCY MARKET TRENDS AND MODERN APPROACHES TO ITS SOLUTION
DOI:
https://doi.org/10.20998/2413-3000.2024.8.6Keywords:
forecasting, cryptocurrency market, time series, machine learning, neural networks, deep learning, hybrid modelAbstract
The current problem of forecasting trends in the cryptocurrency market and modern approaches to solving them are considered. Two main factors have been identified that influence the value of cryptocurrency: the size of the cryptocurrency market and the growth rate of market volumes. The results of research on the prospects of the crypto market are presented, including the fact that Bitcoin in the future may be a protection against the fall of the US dollar for financial market participants. Researchers also view bitcoins not as cash, but as an investment asset. It is concluded that regulation and economic policies related to the use of cryptocurrencies are gradually being strengthened by many countries as its investment attractiveness increases. An analysis of the problem of forecasting the cryptocurrency market trend is presented. An analysis of research and publications on methods for predicting the value of cryptocurrency is presented. Traditional time series forecasting models, such as the ARIMA model, are effective for financial forecasting, but their use is less effective for markets with high volatility, which is typical for cryptocurrencies. Cryptocurrency price forecasting is a time series problem that can be solved using regression and other machine learning techniques. The results of modern research into the potential of machine learning in identifying complex trends and patterns are presented. It has been proven that deep learning methods can be effective in predicting time series with significant fluctuations and almost chaotic and unpredictable behavior. It is concluded that the main aspect is to create flexible models that can adapt to new data and changes in market dynamics. Combining traditional technical factor analysis techniques with innovative machine learning techniques can result in powerful hybrid models. These models use both quantitative and qualitative data to develop better forecasts. The feasibility of developing software systems that implement modern methods of artificial intelligence, including machine learning, deep learning, natural language processing and other technologies to provide market analysis, identify patterns and forecast crypto market trends is substantiated. The use of such software will assist investors in identifying potentially profitable investment opportunities, managing risks and making informed decisions in conditions of high uncertainty.
References
An J., Dorofeev M. Short-term foreign exchang forecasting: decision making based on expert polls. Investment Management and Financial Innovations, 2019. Vol. 16(4). Рp. 215-228. DOI:10.21511/imfi.16(4).2019.19
An J., Dorofeev M., Zhu S. Development of Energy Cooperation between Russia and China. International Journal of Energy Economics and Policy, Econjournals, 2020. Vol. 10(1). Pp 134-139. DOI:10.32479/ijeep.8509
Mikhaylov, A., Danish, M.S.S., Senjyu, T. A New Stage in the Evolution of Cryptocurrency Markets: Analysis by Hurst Method. Dinçer, H. and Yüksel, S. (Ed.) Strategic Outlook in Business and Finance Innovation: Multidimensional Policies for Emerging Economies. Emerald Publishing Limited, Leeds, 2021. Pp. 35-45. DOI:10.1108/978-1-80043-444-820211004
Nasirtafreshi I. Forecasting cryptocurrency prices using Recurrent Neural Network and Long Short-term Memory. Data & Knowledge Engineering, 2022. Vol. 139 (4). DOI:10.1016/j.datak.2022.102009.
Huang N. E., Shen Z., Longet S. R. at al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis. Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. DOI:10.1098/rspa.1998.0193.
Bouoiyour J., Selmi R., Tiwari A. K., Olayeni O. R. Bitcoin: competitor or complement to gold? Economics Bulletin, AccessEcon, 2019. Vol. 39(1). Pp. 186-191. URL: https://www.researchgate.net/publication/330501039_Bitcoin_competitor_or_complement_to_gold (дата звернення: 31.01.2024)
Olvera-Juarez D., Huerta-Manzanilla E. Forecasting Bitcoin pricing with hybrid models: a review of the literature. International Journal of Advanced Engineering Research and Science, 2019. Vol.6(9). Рp.161–164. DOI:10.22161/ijaers.69.18
Rebelo, Rui; Ramos, Patrícia; Santos, Nicolau. Performance of state space and ARIMA models for consumer retail sales forecasting. Robotics and Computer-Integrated Manufacturing, 2015 Vol. 34. Pp. 151-163. DOI: 10.1016/j.rcim.
Siami-Namini S., Tavakoli N., Namin A. S. A comparison of ARIMA and LSTM in forecasting time series. 7th IEEE International Conference on Machine Learning and Applications, 2018. Pp. 1394-1401. DOI 10.1109/ICMLA.2018.00227.
Giot, P., Laurent S., Petitjean M. Trading activity, realized volatility and jumps. Journal of Empirical Finance, 2010. Vol.17(1). Рp.168-175. DOI:10.1016/j.jempfin.2009.07.001
Zhang P.G. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, Vol.50, Рp.159-175. DOI:10.1016/S0925-2312(01)00702-0
Xu W., Hui P., Zeng X., Zhou F., Tian X, Xiaoying P. A hybrid modelling method for time series forecasting based on a linear regression model and deep learning. Appl Intell, 2019. Vol.49, Рp.3002–3015. DOI:10.1007/s10489-019-01426-3
Lai, Robert K.; Fan, Chin-Yuan; Huang, Wei-Hsiu; Chang, Pei-Chann. "Evolving and clustering fuzzy decision tree for financial time series data forecasting. Expert Systems with Applications, 2009. Vol. 36 (2), Part 2. Pp. 3761-3773. DOI:10.1016/j.eswa.2008.02.025
Yan X. Forecasting Cryptocurrency Prices. URL: https://www.imperial.ac.uk/media/imperial-college/faculty-of-natural-sciences/department-of-mathematics/math-finance/Forecasting_cryptocurrency_prices.pdf (дата звернення: 31.01.2024)
Ramadani K., Devianto D. The forecasting model of Bitcoin price with fuzzy time series Markov chain and chen logical method. AIP Conference Proceedings. 2020. Vol. 2296, 020095. P.1-11. DOI:10.1063/5.0032178.
Derbentsev V. Forecasting Cryptocurrency Prices Using Ensembles-Based Machine Learning Approach. 2020 IEEE International Conference on Problems of Infocommunications. Science and Technology (PIC S&T). DOI:10.1109/PICST51311.2020.9468090
Derbentsev V., Matviychuk A., Soloviev V.N. Forecasting of Cryptocurrency Prices Using Machine Learning. Advanced Studies of Financial Technologies and Cryptocurrency Markets, 2020. Pp. 211–231.
Zhang Z., Zhou J., Mondalet S., Dai H-N. Forecasting cryptocurrency price using convolutional neural networks with weighted and attentive memory channels. Expert Systems with Applications, 2021. Vol. 183, 115378. Pp. DOI:10.1016/j.eswa.2021.115378
Jay P., Kalariya V., Parmar P., Tanwar S. Stochastic neural networks for cryptocurrency price prediction. IEEE Access, 2020. Vol. 8. P. 82804–82818. DOI:10.1109/ACCESS.2020.2990659
Sebastião, H.; Godinho, P. Forecasting and trading cryptocurrencies with machine learning under changing market conditions. Financial Innovation, 2021. Vol. 7. Pp. 1–30. DOI:10.1186/s40854-020-00217-x
Akyildirim E., Goncuy A., Sensoy A. Prediction of Cryptocurrency Returns Using Machine Learning. URL: https://www.researchgate.net/publication/329322600, 25.04.2023.
Pintelas E., Stavroyiannis S., Livieris I., Kotsilieris T. Investigating the Problem of Cryptocurrency Price Prediction: A Deep Learning Approach. Artificial Intelligence Applications and Innovations. 2020. Publisher: Springer International Publishing. Pp.99-110. DOI:10.1007/978-3-030-49186-4_9.
Jiang X. Bitcoin price prediction based on deep learning methods. Journal of Mathematical Finance, 2019. Vol.10. Pp. 132–139. DOI:10.4236/jmf.2020.101009
Politis A., Doka K., Koziris N. Ether price prediction using advanced deep learning models. Proceedings of the 2021 IEEE International Conference on Blockchain and Cryptocurrency (ICBC), 2021. Pp.1–3. DOI: 10.1109/ICBC51069.2021.9461061
Livieris I. E., Kiriakidou N., Stavroyiannis S., Pintelas P. E. An advanced CNN-LSTM model for cryptocurrency forecasting. Electronics, 2021. Vol. 10, 287. Pp. DOI:10.3390/electronics10030287, 25.04.2023.
Fawaz I. Deep learning for time series classification: a review. /Data Mining and Knowledge Discovery, 2019. Vol. 33(4). Pp. 917–963. DOI:10.1007/s10618-019-00619-1.
Saadah S., Whafa A. A. Monitoring Financial Stability Based on Prediction of Cryptocurrencies Price Using Intelligent Algorithm. 2020 International Conference on Data Science and its Applications (ICoDSA), 2020. Pp. 1–10. DOI:10.1109/ICoDSA50139.2020.9212968.
Kang C.Y., Lee C.P., Lim K.M. Cryptocurrency Price Prediction with Convolutional Neural Network and Stacked Gated Recurrent Unit. Data. 2022. Vol. 7 (11), 149. Pp. DOI:10.3390/data7110149
Tanwar S., Patel N., Patel S. N. Deep learning-based cryptocurrency price prediction scheme with inter-dependent relations. IEEE Access, 2021.Vol. 9. Pp. 138633–138646. DOI:10.1109/ACCESS.2021.3117848
Gurgul V., Lessmann S., Härdle W. K. K. Forecasting Cryptocurrency Prices Using Deep Learning: Integrating Financial, Blockchain, and Text Data. arXiv preprint arXiv:2311.14759, 2023. Pp.1-35. DOI:10.48550/arXiv.2311.14759.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our journal abides by the Creative Commons copyright rights and permissions for open access journals.
Authors who publish with this journal agree to the following terms:
Authors hold the copyright without restrictions and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-commercial and non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their published work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
