Received:
2024-02-12 | Accepted:
2024-05-08 | Published:
2024-06-30
Title
Cryptocurrency price forecasting: a comparative analysis of autoregressive and recurrent neural network models
Abstract
This article presents a novel approach to cryptocurrency price forecasting, leveraging advanced machine-learning techniques. By comparing traditional autoregressive models with recurrent neural network approaches, the study aims to evaluate the forecasting accuracy of Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models across various cryptocurrencies, including Bitcoin, Ethereum, Dogecoin, Polygon, and Toncoin. The data for this empirical study was sourced from historical prices of these specific cryptocurrencies, as recorded on the CoinMarketCap platform, covering January 2022 to April 2024. The methodology employed involves rigorous statistical and neural network modelling where each model's parameters were meticulously optimized for the specific characteristics of each cryptocurrency's price data. Performance metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) were used to assess the precision of each model. The main results indicate that LSTM and GRU models, leveraging deep learning techniques, generally outperformed the traditional ARIMA and SARIMA models regarding error metrics. This demonstrates a higher efficacy of neural networks in handling the non-linear complexities and volatile nature of cryptocurrency price movements. This study contributes to the ongoing discourse in financial technology by elucidating the practical implications of using advanced machine-learning techniques for economic forecasting. Importantly, it provides valuable insights that can directly inform and enhance the decision-making processes of investors and traders in digital assets.
Keywords
forecasting, prediction, cryptocurrencies, time series, ARIMA, SARIMA, RNN, LSTM, GRU
JEL classifications
C22
, C32
, C45
, C53
, G17
URI
http://jssidoi.org/jesi/article/1212
DOI
Pages
425-436
Funding
This is an open access issue and all published articles are licensed under a
Creative Commons Attribution 4.0 International License
References
Apostolakis, G.N. (2024). Bitcoin price volatility transmission between spot and futures markets. International Review of Financial Analysis, 94, Article Number 103251 http://doi.org/10.1016/j.irfa.2024.103251
Search via ReFindit
Au, C.H., Li, G., Hsu, W.S. Shieh, P.H., Law, K.M.Y. (2024). Characteristics of proliferating cryptocurrencies: a comparative study between stable and non-stable cryptocurrencies. Enterprise Information Systems http://doi.org/10.1080/17517575.2024.2356771
Search via ReFindit
Bâra, A., Oprea, S.V., & Panait, M. (2024). Insights into Bitcoin and energy nexus. A Bitcoin price prediction in bull and bear markets using a complex meta model and SQL analytical functions. Applied Intelligence http://doi.org/10.1007/s10489-024-05474-2
Search via ReFindit
Bielskis, A., & Belovas, I. (2022). Comparative analysis of stock price ARIMA and LSTM forecasting methods. Lietuvos Matematikos Rinkinys, 63. https://doi.org/10.15388/lmr.2022.29755
Search via ReFindit
Box, G. E. P., & Jenkins, G. M. 1970. Time Series Analysis: Forecasting and Control. Holden-Day, San Francisco.
Search via ReFindit
Box, G. E. P., & Jenkins, G. M. 1976. Time Series Analysis: Forecasting and Control. Revised Edition, Holden-Day, San Francisco.
Search via ReFindit
Brichta, M. (2023). Fanning Money: The Cultural Economy and Participatory Politics of Dogecoin. International Journal of Communication, 17(2023), 6032-6050. Retrieved from https://ijoc.org/index.php/ijoc/article/download/21030/4337
Search via ReFindit
Buterin, V. (2013). Ethereum White Paper: A Next-Generation Smart Contract and Decentralized Application Platform. Retrieved from https://blockchainlab.com/pdf/Ethereum_white_paper-a_next_generation_smart_contract_and_decentralized_application_platform-vitalik-buterin.pdf
Search via ReFindit
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014). On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation. https://doi.org/10.3115/v1/w14-4012
Search via ReFindit
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://doi.org/10.3115/v1/d14-1179
Search via ReFindit
Corrêa, J. M., Neto, A. C., Teixeira Júnior, L. A., Franco, E. M. C., & Faria, A. E. (2016). Time Series Forecasting with the WARIMAX-GARCH Method. Neurocomputing, 216, 805-815. https://doi.org/10.1016/j.neucom.2016.08.046
Search via ReFindit
Demirel, E. (2024). A comparison of arch models: the determinants of bitcoin's price. Academy Review, 1, 141-149. http://doi.org/10.32342/2074-5354-2024-1-60-10
Search via ReFindit
Gopu, A., Ramakrishnan, A., Balasubramanian, G., & Srinidhi, K. (2023). A Comparative Study on Forest Fire Prediction using ARIMA, SARIMA, LSTM, and GRU Methods. 2023 IEEE International Conference on Contemporary Computing and Communications (InC4). https://doi.org/10.1109/inc457730.2023.10262965
Search via ReFindit
Hochreiter, S., & Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
Search via ReFindit
Jisha, R. C., Nazeer, H., & Kavya, R. (2023). Hybridizing Statistical and Neural Network Models for Enhanced Stock Price Forecasting. 2023 4th IEEE Global Conference for Advancement in Technology (GCAT). https://doi.org/10.1109/gcat59970.2023.10353309
Search via ReFindit
Kapur, G., Manohar, S., Mittal, A., Jain, V., & Trivedi, S. (2024). Cryptocurrency price fluctuation and time series analysis through candlestick pattern of bitcoin and ethereum using machine learning. International Journal of Quality & Reliability Management http://doi.org/10.1108/IJQRM-12-2022-0363
Search via ReFindit
Li, Z., & Zhao, J. (2022). Stock price prediction based on ARIMA-PCA-BP hybrid model. 2022 2nd International Signal Processing, Communications and Engineering Management Conference (ISPCEM). https://doi.org/10.1109/ispcem57418.2022.00058
Search via ReFindit
Nakamoto, S. (2008). Bitcoin: A Peer-to-Peer Electronic Cash System. Retrieved from https://bitcoin.org/bitcoin.pdf
Search via ReFindit
Ng, K. Y., Zainal, Z., & Samsudin, S. (2023). Comparative Performance of ARIMA, SARIMA and GARCH Models in Modelling and Forecasting Unemployment Among ASEAN-5 Countries. International Journal of Business and Society, 24(3), 967-994. https://doi.org/10.33736/ijbs.6393.2023
Search via ReFindit
Nosouhian, S., Nosouhian, F., & Kazemi Khoshouei, A. (2021). A Review of Recurrent Neural Network Architecture for Sequence Learning: Comparison between LSTM and GRU. https://doi.org/10.20944/preprints202107.0252.v1
Search via ReFindit
Respaty, W. A., Hong, C., Putra, N. K., Kurniadi, F. I., & Riccosan. (2023). Weather Prediction in Jakarta: An Analysis of Climate Data and Regional Influences using LSTM and GRU. 2023 International Conference on Data Science and Its Applications (ICoDSA). https://doi.org/10.1109/icodsa58501.2023.10277097
Search via ReFindit
Satheesh, A., & Sundararagan, S. (2022). An analysis of the feasibility of SARIMAX-GARCH through load forecasting. Journal of Emerging Investigators. https://doi.org/10.59720/22-085
Search via ReFindit
Sehrawat, P. K., & Vishwakarma, D. K. (2022). Comparative Analysis of Time Series Models on COVID-19 Predictions. 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS). https://doi.org/10.1109/icscds53736.2022.9760992
Search via ReFindit
Si, Y. (2023). Modeling Opening Price Spread of Shanghai Composite Index Based on ARIMA-GRU/LSTM Hybrid Model. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4493799
Search via ReFindit
Singh, S., Pise, A, & Yoon, B. (2024). Prediction of bitcoin stock price using feature subset optimization. Heliyon, 10(7). Article Number e28415 http://doi.org/10.1016/j.heliyon.2024.e28415
Search via ReFindit
Vo, N., & Ślepaczuk, R. (2022). Applying Hybrid ARIMA-SGARCH in Algorithmic Investment Strategies on S&P500 Index. Entropy, 24(2), 158. https://doi.org/10.3390/e24020158
Search via ReFindit
Zarzycki, K., & Ławryńczuk, M. (2021). LSTM and GRU Neural Networks as Models of Dynamical Processes Used in Predictive Control: A Comparison of Models Developed for Two Chemical Reactors. Sensors, 21(16), 5625. https://doi.org/10.3390/s21165625
Search via ReFindit
Zhang, Y., Wang, J., & Zhang, X. (2021). Conciseness is better: Recurrent attention LSTM model for document-level sentiment analysis. Neurocomputing, 462, 101-112. https://doi.org/10.1016/j.neucom.2021.07.072
Search via ReFindit
RSS 1.0
