Predicting Cryptocurrency Prices with a Hybrid ARIMA and LSTM Model
Main Article Content
Keywords
Cryptocurrency, Price Prediction, Deep Learning, Blockchain, Digital Investment
Abstract
Cryptocurrencies have attracted significant attention from investors, regulators and the media since their emergence. In a world where digital advancements are increasingly included in everyday relations, studying the behaviour of cryptocurrencies and their impact on financial markets becomes a necessity. This paper introduces a comparative analysis towards a hybrid model combining classical and modern methods for predicting cryptocurrency prices. This study deals with everyday recordings of 10 cryptocurrencies that represent different technological innovations and use cases. Studying these cryptocurrencies can help understand volatility, volumes and price movements. We aim to develop a time series statistical model and to study the effectiveness of deep learning (DL) models, specifically long short-term memory (LSTM) model and the autoregressive integrated moving average (ARIMA) model, for predicting cryptocurrency prices accurately and forecasting stationary data. Combining ARIMA and LSTM, we managed to obtain a high value of R² for Binance Coin (BNB) cryptocurrency (0.936) with an average R² for all evaluated cryptocurrencies of 0.6555.
References
Bose, S., Dong, G., Simpson, A., Bose, S., Dong, G., & Simpson, A. (2019). The financial ecosystem (pp. 19-46). Springer International Publishing.
Box, G.E., & Pierce, D.A. (1970). Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. Journal of the American statistical Association , 65 (332), 1509-1526.
Brockwell, P.J., Davis, R.A. (2016). Nonstationary and seasonal time series models. Introduction to time series and forecasting , 157-193.
Chaum, D. (1983). Blind signatures for untraceable payments. In Advances in Cryptology: Proceedings of Crypto 82 (pp. 199-203). Boston, MA: Springer US.
Chen, Y., & Wang, J. (2024). Exploring Attention Mechanisms in Financial Time Series Forecasting. Journal of Financial Markets, 60, 124-140. https://doi:10.1016/j.finmar.2023.01.004.
Chen, Y., & Wang, J. (2024). Transformers for Time Series Forecasting: A Comprehensive Survey.IEEE Transactions on Neural Networks and Learning Systems, 35(4), 789-805. https://doi:10.1109/TNNLS.2023.3287512.
Corbet, S., Lucey, B., Urquhart, A., & Yarovaya, L. (2019). Cryptocurrencies as a financial asset: A systematic analysis. International Review of Financial Analysis, 62, 182-199.https://doi.org/10.1016/j.irfa.2018.09.003.
Cortez, K., Rodríguez-García, M. D. P., & Mongrut, S. (2020). Exchange market liquidity prediction with the K-nearest neighbor approach: Crypto vs. fiat currencies. Mathematics, 9(1), 56.https://doi.org/10.3390/math9010056.
Du, Y., Côté, B., & Liu, F. (2024). A Self-Attention Mechanism for Learning Missing Values in Time Series Forecasting.Journal of Time Series Analysis, 45(1), 78-95. https://doi:10.1111/jtsa.12678.
Fahad, S., & Awan, I. (2022). Combining Machine Learning Techniques for Financial Forecasting: An Application in Cryptocurrency.Expert Systems with Applications, 190, 116077. https://doi:10.1016/j.eswa.2021.116077.
Fang, Z., Qajar, J., Safari, K., Hosseini, S., Khajehzadeh, M., & Nehdi, ML (2023). Application of non-destructive test results to estimate rock mechanical characteristics—A case study. Minerals , 13 (4), 472.https://doi.org/10.3390/min13040472.
Hossain, M. S., & Muhammad, A. (2023). Hybrid Machine Learning Techniques for Cryptocurrency Price Prediction: A Comprehensive Study.Journal of Computational Science, 63, 101678. https://doi:10.1016/j.jocs.2023.101678.
Jalan, A., Matkovskyy, R., Urquhart, A., & Yarovaya, L. (2023). The role of interpersonal trust in cryptocurrency adoption. Journal of International Financial Markets, Institutions and Money , 83 , 101715.https://doi.org/10.1016/j.intfin.2022.101715.
Jaquart, P., Köpke, S., & Weinhardt, C. (2022). Machine learning for cryptocurrency market prediction and trading. The Journal of Finance and Data Science, 8, 331-352.https://doi.org/10.1016/j.jfds.2022.12.001.
Jiang, X., & Zhang, H. (2020). A Comparative Study of Machine Learning Algorithms for Financial Time Series Prediction. Journal of Computational and Theoretical Nanoscience, 17(12), 1-8. https://doi:10.1166/jctn.2020.10000.
Karami, A., & Khatami, S. (2021). Forecasting Cryptocurrency Prices Using Machine Learning Models: A Review.International Journal of Financial Studies, 9(2), 27. https://doi:10.3390/ijfs9020027.
Kim, D., Park, J., & Lee, H. (2023). Integrating CNNs and Attention Mechanisms for Enhanced Cryptocurrency Price Prediction. Journal of Computational Finance, 27(1), 15-30. https://doi:10.21314/JCF.2023.365.
Koo, H. Y., & Kim, D. H. (2024). Enhancing Financial Time Series Prediction with Transformer Networks.Journal of Forecasting, 43(3), 456-472. https://doi:10.1002/for.2973.
Li, Y., Zhang, W., & Yang, X. (2023). The Time-Series Transformer: Enhancing Forecasting Performance and Efficiency. Journal of Machine Learning Research, 24(120), 1-23. https://doi:10.5555/12345678.
Lim, B., Arık, S. Ö., Loeff, N., & Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4), 1748-1764.https://doi.org/10.1016/j.ijforecast.2021.03.012.
Liu, Y., & Zhang, J. (2023). Feature Selection and Model Ensemble for Cryptocurrency Price Prediction. Journal of Economic Dynamics and Control, 133, 104047. https://doi:10.1016/j.jedc.2022.104047.
McCarthy, P.X., Gong, X., Eghbal, S., Falster, D.S., & Rizoiu, M.A. (2021). Evolution of diversity and dominance of companies in online activity. Plos one , 16 (4), e0249993. https://doi.org/10.1371/journal.pone.0249993.
Mohammadabadi, S. M. S., Zawad, S., Yan, F., & Yang, L. (2023). Speed up federated learning in heterogeneous environment: A dynamic tiering approach. arXiv preprint arXiv:2312.05642.https://doi.org/10.48550/arXiv.2312.05642.
Moussa, A., & Faye, I. (2021).ARIMA-GARCH Approach to Cryptocurrency Volatility Prediction. Financial Innovation, 7(1), 1-15. https://doi:10.1186/s40854-021-00257-5.
Nguyen, D. K., & Vo, X. V. (2021). A Combined ARIMA-GARCH Model for Predicting Cryptocurrency Prices. Mathematics, 9(2), 234. https://doi:10.3390/math9020234.
Omar, A. F., & Soliman, A. (2023). Predicting Stock Prices using Machine Learning Techniques: A Study of SVM, Decision Trees, and Random Forest. Applied Sciences, 13(6), 2980. https://doi: 10.3390/app13062980.
Omran, N. F., Abd-el Ghany, S. F., Saleh, H., Ali, A. A., Gumaei, A., & Al-Rakhami, M. (2021). Applying deep learning methods on time‐series data for forecasting COVID‐19 in Egypt, Kuwait, and Saudi Arabia. Complexity, 6686745. https://doi.org/10.1155/2021/6686745.
Orte, F., Mira, J., Sánchez, M. J., & Solana, P. (2023). A random forest-based model for crypto asset forecasts in futures markets with out-of-sample prediction. Research in International Business and Finance, 64, 101829.https://doi.org/10.1016/j.ribaf.2022.101829.
Patel, H., & Kumar, A. (2023). Deep Learning Models for Cryptocurrency Price Forecasting: A Review.Journal of Financial Stability, 65, 100972. https://doi:10.1016/j.jfs.2023.100972.
Patel, R., & Thakur, M. (2024). Utilizing ARIMA and GARCH Models for Predictive Analytics in Cryptocurrencies. International Journal of Financial Studies, 12(1), 55-75. https://doi:10.3390/ijfs12010055.
Ramakrishnan, R., Vadakedath, A., Bhaskar, A., Sachin Kumar, S., & Soman, KP (2022). Data-Driven Volatile Cryptocurrency Price Forecasting via Variational Mode Decomposition and BiLSTM. In International Conference on Innovative Computing and Communications: Proceedings of ICICC 2022, Volume 1 (pp. 651-663).
Raza, S. A., & Riaz, S. (2020).Modeling and Forecasting Bitcoin Returns Using GARCH Models: Evidence from Pakistan.Journal of Risk and Financial Management, 13(11), 267. https://doi:10.3390/jrfm13110267.
Sridhar, A., & Sanagavarapu, P. (2023). Multi-Head Self-Attention Transformer for Cryptocurrency Price Prediction. International Journal of Financial Studies, 11(3), 45-58. https://doi:10.3390/ijfs11030045.
Safari, K., Khalfalla, S., & Imani, F. (2022, October). Dependency evaluation of defective formation and printing location in additive manufacturing. In ASME International Mechanical Engineering Congress and Exposition (Vol. 86632, p. V02AT02A016). American Society of Mechanical Engineers.https://doi.org/10.1115/IMECE2022-95145.
Son, H., Lee, J., & Kim, M. (2022). Predicting Cryptocurrency Prices by Analyzing Social Media Trends.Journal of Financial Technology, 1(2), 34-50. https://doi:10.1016/j.jft.2022.05.002.
Tanwar, S., & Kumar, V. (2023). Advanced Deep Learning Techniques for Cryptocurrency Price Forecasting: A Review. Journal of Computational Finance, 28(1), 1-19. https://doi:10.21314/JCF.2023.400.
Urquhart Andrew & Yarovaya Larisa, Cryptocurrency research: future directions. The European Journal of Finance, 2023. https://doi.org/10.1080/1351847X.2023.2284186
You, H., Xu, Z., & Li, T. (2023). Spatiotemporal Transformer for Short-Term Time-Series Data Prediction.IEEE Transactions on Neural Networks and Learning Systems, 35(2), 512-526. https://doi:10.1109/TNNLS.2023.3287547.
Yunsi, S., Lahcen, A., & Azzouz Mohamed, A. (2024). Transformer Neural Networks for Cryptocurrency Price Prediction. Journal of Financial Stability, 70, 101029. https://doi:10.1016/j.jfs.2023.101029.
Wegayehu, E. B. & Muluneh, F. B. (2022). Short-Term Daily Univariate StreamflowForecasting Using Deep Learning Models. Advances in Meteorology.https://doi:10.1155/2022/1860460.
Wu, J., Zhang, X., Huang, F., Zhou, H., & Chandra, R. (2024). Review of deep learning models for crypto price prediction: implementation and evaluation. arXiv preprint arXiv:2405.11431 .
https://doi.org/10.48550/arXiv.2405.11431.
Zhang, S., Li, Y., & Zhao, Q. (2023). Dual-Stage Attention Mechanism for Time Series Forecasting: A Case Study on Cryptocurrency Prices. Applied Intelligence, 53(5), 6789-6803. https://doi:10.1007/s10489-022-03145-1.
Zhang, Z., Dai, H. N., Zhou, J., Mondal, S. K., García, M. M., & Wang, H. (2021). Forecasting cryptocurrency price using convolutional neural networks with weighted and attentive memory channels. Expert Systems with Applications, 183, 115378.https://doi.org/10.1016/j.eswa.2021.115378
Zhang, Y., & Wang, S. (2020). "Cryptocurrency Price Prediction Using Time Series Analysis: An ARIMA Approach." Journal of Applied Statistics, 47(1), 45-61. https://doi:10.1080/02664763.2019.1610860.
Box, G.E., & Pierce, D.A. (1970). Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. Journal of the American statistical Association , 65 (332), 1509-1526.
Brockwell, P.J., Davis, R.A. (2016). Nonstationary and seasonal time series models. Introduction to time series and forecasting , 157-193.
Chaum, D. (1983). Blind signatures for untraceable payments. In Advances in Cryptology: Proceedings of Crypto 82 (pp. 199-203). Boston, MA: Springer US.
Chen, Y., & Wang, J. (2024). Exploring Attention Mechanisms in Financial Time Series Forecasting. Journal of Financial Markets, 60, 124-140. https://doi:10.1016/j.finmar.2023.01.004.
Chen, Y., & Wang, J. (2024). Transformers for Time Series Forecasting: A Comprehensive Survey.IEEE Transactions on Neural Networks and Learning Systems, 35(4), 789-805. https://doi:10.1109/TNNLS.2023.3287512.
Corbet, S., Lucey, B., Urquhart, A., & Yarovaya, L. (2019). Cryptocurrencies as a financial asset: A systematic analysis. International Review of Financial Analysis, 62, 182-199.https://doi.org/10.1016/j.irfa.2018.09.003.
Cortez, K., Rodríguez-García, M. D. P., & Mongrut, S. (2020). Exchange market liquidity prediction with the K-nearest neighbor approach: Crypto vs. fiat currencies. Mathematics, 9(1), 56.https://doi.org/10.3390/math9010056.
Du, Y., Côté, B., & Liu, F. (2024). A Self-Attention Mechanism for Learning Missing Values in Time Series Forecasting.Journal of Time Series Analysis, 45(1), 78-95. https://doi:10.1111/jtsa.12678.
Fahad, S., & Awan, I. (2022). Combining Machine Learning Techniques for Financial Forecasting: An Application in Cryptocurrency.Expert Systems with Applications, 190, 116077. https://doi:10.1016/j.eswa.2021.116077.
Fang, Z., Qajar, J., Safari, K., Hosseini, S., Khajehzadeh, M., & Nehdi, ML (2023). Application of non-destructive test results to estimate rock mechanical characteristics—A case study. Minerals , 13 (4), 472.https://doi.org/10.3390/min13040472.
Hossain, M. S., & Muhammad, A. (2023). Hybrid Machine Learning Techniques for Cryptocurrency Price Prediction: A Comprehensive Study.Journal of Computational Science, 63, 101678. https://doi:10.1016/j.jocs.2023.101678.
Jalan, A., Matkovskyy, R., Urquhart, A., & Yarovaya, L. (2023). The role of interpersonal trust in cryptocurrency adoption. Journal of International Financial Markets, Institutions and Money , 83 , 101715.https://doi.org/10.1016/j.intfin.2022.101715.
Jaquart, P., Köpke, S., & Weinhardt, C. (2022). Machine learning for cryptocurrency market prediction and trading. The Journal of Finance and Data Science, 8, 331-352.https://doi.org/10.1016/j.jfds.2022.12.001.
Jiang, X., & Zhang, H. (2020). A Comparative Study of Machine Learning Algorithms for Financial Time Series Prediction. Journal of Computational and Theoretical Nanoscience, 17(12), 1-8. https://doi:10.1166/jctn.2020.10000.
Karami, A., & Khatami, S. (2021). Forecasting Cryptocurrency Prices Using Machine Learning Models: A Review.International Journal of Financial Studies, 9(2), 27. https://doi:10.3390/ijfs9020027.
Kim, D., Park, J., & Lee, H. (2023). Integrating CNNs and Attention Mechanisms for Enhanced Cryptocurrency Price Prediction. Journal of Computational Finance, 27(1), 15-30. https://doi:10.21314/JCF.2023.365.
Koo, H. Y., & Kim, D. H. (2024). Enhancing Financial Time Series Prediction with Transformer Networks.Journal of Forecasting, 43(3), 456-472. https://doi:10.1002/for.2973.
Li, Y., Zhang, W., & Yang, X. (2023). The Time-Series Transformer: Enhancing Forecasting Performance and Efficiency. Journal of Machine Learning Research, 24(120), 1-23. https://doi:10.5555/12345678.
Lim, B., Arık, S. Ö., Loeff, N., & Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4), 1748-1764.https://doi.org/10.1016/j.ijforecast.2021.03.012.
Liu, Y., & Zhang, J. (2023). Feature Selection and Model Ensemble for Cryptocurrency Price Prediction. Journal of Economic Dynamics and Control, 133, 104047. https://doi:10.1016/j.jedc.2022.104047.
McCarthy, P.X., Gong, X., Eghbal, S., Falster, D.S., & Rizoiu, M.A. (2021). Evolution of diversity and dominance of companies in online activity. Plos one , 16 (4), e0249993. https://doi.org/10.1371/journal.pone.0249993.
Mohammadabadi, S. M. S., Zawad, S., Yan, F., & Yang, L. (2023). Speed up federated learning in heterogeneous environment: A dynamic tiering approach. arXiv preprint arXiv:2312.05642.https://doi.org/10.48550/arXiv.2312.05642.
Moussa, A., & Faye, I. (2021).ARIMA-GARCH Approach to Cryptocurrency Volatility Prediction. Financial Innovation, 7(1), 1-15. https://doi:10.1186/s40854-021-00257-5.
Nguyen, D. K., & Vo, X. V. (2021). A Combined ARIMA-GARCH Model for Predicting Cryptocurrency Prices. Mathematics, 9(2), 234. https://doi:10.3390/math9020234.
Omar, A. F., & Soliman, A. (2023). Predicting Stock Prices using Machine Learning Techniques: A Study of SVM, Decision Trees, and Random Forest. Applied Sciences, 13(6), 2980. https://doi: 10.3390/app13062980.
Omran, N. F., Abd-el Ghany, S. F., Saleh, H., Ali, A. A., Gumaei, A., & Al-Rakhami, M. (2021). Applying deep learning methods on time‐series data for forecasting COVID‐19 in Egypt, Kuwait, and Saudi Arabia. Complexity, 6686745. https://doi.org/10.1155/2021/6686745.
Orte, F., Mira, J., Sánchez, M. J., & Solana, P. (2023). A random forest-based model for crypto asset forecasts in futures markets with out-of-sample prediction. Research in International Business and Finance, 64, 101829.https://doi.org/10.1016/j.ribaf.2022.101829.
Patel, H., & Kumar, A. (2023). Deep Learning Models for Cryptocurrency Price Forecasting: A Review.Journal of Financial Stability, 65, 100972. https://doi:10.1016/j.jfs.2023.100972.
Patel, R., & Thakur, M. (2024). Utilizing ARIMA and GARCH Models for Predictive Analytics in Cryptocurrencies. International Journal of Financial Studies, 12(1), 55-75. https://doi:10.3390/ijfs12010055.
Ramakrishnan, R., Vadakedath, A., Bhaskar, A., Sachin Kumar, S., & Soman, KP (2022). Data-Driven Volatile Cryptocurrency Price Forecasting via Variational Mode Decomposition and BiLSTM. In International Conference on Innovative Computing and Communications: Proceedings of ICICC 2022, Volume 1 (pp. 651-663).
Raza, S. A., & Riaz, S. (2020).Modeling and Forecasting Bitcoin Returns Using GARCH Models: Evidence from Pakistan.Journal of Risk and Financial Management, 13(11), 267. https://doi:10.3390/jrfm13110267.
Sridhar, A., & Sanagavarapu, P. (2023). Multi-Head Self-Attention Transformer for Cryptocurrency Price Prediction. International Journal of Financial Studies, 11(3), 45-58. https://doi:10.3390/ijfs11030045.
Safari, K., Khalfalla, S., & Imani, F. (2022, October). Dependency evaluation of defective formation and printing location in additive manufacturing. In ASME International Mechanical Engineering Congress and Exposition (Vol. 86632, p. V02AT02A016). American Society of Mechanical Engineers.https://doi.org/10.1115/IMECE2022-95145.
Son, H., Lee, J., & Kim, M. (2022). Predicting Cryptocurrency Prices by Analyzing Social Media Trends.Journal of Financial Technology, 1(2), 34-50. https://doi:10.1016/j.jft.2022.05.002.
Tanwar, S., & Kumar, V. (2023). Advanced Deep Learning Techniques for Cryptocurrency Price Forecasting: A Review. Journal of Computational Finance, 28(1), 1-19. https://doi:10.21314/JCF.2023.400.
Urquhart Andrew & Yarovaya Larisa, Cryptocurrency research: future directions. The European Journal of Finance, 2023. https://doi.org/10.1080/1351847X.2023.2284186
You, H., Xu, Z., & Li, T. (2023). Spatiotemporal Transformer for Short-Term Time-Series Data Prediction.IEEE Transactions on Neural Networks and Learning Systems, 35(2), 512-526. https://doi:10.1109/TNNLS.2023.3287547.
Yunsi, S., Lahcen, A., & Azzouz Mohamed, A. (2024). Transformer Neural Networks for Cryptocurrency Price Prediction. Journal of Financial Stability, 70, 101029. https://doi:10.1016/j.jfs.2023.101029.
Wegayehu, E. B. & Muluneh, F. B. (2022). Short-Term Daily Univariate StreamflowForecasting Using Deep Learning Models. Advances in Meteorology.https://doi:10.1155/2022/1860460.
Wu, J., Zhang, X., Huang, F., Zhou, H., & Chandra, R. (2024). Review of deep learning models for crypto price prediction: implementation and evaluation. arXiv preprint arXiv:2405.11431 .
https://doi.org/10.48550/arXiv.2405.11431.
Zhang, S., Li, Y., & Zhao, Q. (2023). Dual-Stage Attention Mechanism for Time Series Forecasting: A Case Study on Cryptocurrency Prices. Applied Intelligence, 53(5), 6789-6803. https://doi:10.1007/s10489-022-03145-1.
Zhang, Z., Dai, H. N., Zhou, J., Mondal, S. K., García, M. M., & Wang, H. (2021). Forecasting cryptocurrency price using convolutional neural networks with weighted and attentive memory channels. Expert Systems with Applications, 183, 115378.https://doi.org/10.1016/j.eswa.2021.115378
Zhang, Y., & Wang, S. (2020). "Cryptocurrency Price Prediction Using Time Series Analysis: An ARIMA Approach." Journal of Applied Statistics, 47(1), 45-61. https://doi:10.1080/02664763.2019.1610860.
Article Sidebar
Published
2025-04-14
Article Details
How to Cite
Elamine, M., & Ben Abdallah, A. (2025). Predicting Cryptocurrency Prices with a Hybrid ARIMA and LSTM Model. Journal of Telecommunications and the Digital Economy, 13(1), 98-117. https://doi.org/10.18080/jtde.v13n1.1052
Issue
Section
Special Issue: Driving the Digital Economy
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright Telecommunications Association Inc.
How to Cite
Elamine, M., & Ben Abdallah, A. (2025). Predicting Cryptocurrency Prices with a Hybrid ARIMA and LSTM Model. Journal of Telecommunications and the Digital Economy, 13(1), 98-117. https://doi.org/10.18080/jtde.v13n1.1052
