International Journal of Information Engineering and Electronic Business (IJIEEB)
IJIEEB Vol. 17, No. 5, 8 Oct. 2025
Cover page and Table of Contents: PDF (size: 1533KB)
A Transfer Learning–Enhanced Hybrid Deep Learning Framework for Bitcoin Price Forecasting Using Market Sentiment and Time Series Data
PDF (1533KB), PP.1-17
Views: 0 Downloads: 0
Author(s)
Index Terms
Bitcoin Price Prediction, Hybrid Deep Learning, Transfer Learning, GRU, Bi-LSTM, Multi-Head Attention, Sentiment Analysis, Time-Series Forecasting
Abstract
The extreme volatility of Bitcoin markets makes accurate price prediction notably difficult. This paper proposes a new hybrid deep learning model that incorporates a Gated Recurrent Unit (GRU), a Bidirectional Long Short-Term Memory (Bi LSTM) model, and a Multi Head Attention mechanism to permit the model to utilize both historical price data and sentiment information from Twitter. We constructed the model utilizing a two-stage transfer learning approach: we first pretrained the model on data from 2017−2019 to learn lower-level fluctuation behaviors, then we fine-tuned the model on data from 2021−2023 in order to be sensitive to recent market behaviors. The model performed exceptionally well against multiple state-of-the-art baselines using root mean square error (RMSE) and mean absolute error (MAE) metrics, reporting RMSE values of 679.61 and MAE of 452.95, achieving considerable improvement over the baseline models. Our experimental results show that leveraging Twitter sentiment greatly improved trend prediction. In addition, our benchmarks showed that our method performed better than the existing methods. Furthermore, our ablation studies illustrated how each particular feature performed. Overall, our results demonstrate that multi-scale temporal modeling combined with social media sentiment integration produces a scalable and resilient solution to combat the challenges of volatility to forecast cryptocurrency prices accurately and efficiently.
Cite This Paper
Rachid Bourday, Issam Aattouchi, Mounir Ait Kerroum, "A Transfer Learning–Enhanced Hybrid Deep Learning Framework for Bitcoin Price Forecasting Using Market Sentiment and Time Series Data", International Journal of Information Engineering and Electronic Business(IJIEEB), Vol.17, No.5, pp. 1-17, 2025. DOI:10.5815/ijieeb.2025.05.01
Reference
[1]Kaushal, R. (2016). Bitcoin: First Decentralized Payment System. International Journal of Engineering and Computer Science, 5(5), 16514–16517. doi:10.18535/ijecs/v5i5.30.
[2]Oliver, J. (2013). Mastering blockchain distributed ledger technology, and smart contracts explained. Packt Publishing, Birmingham, United Kingdom.
[3]Dudek, Grzegorz, Fiszeder, Piotr, Kobus, Pawe, and Orzeszko, Witold. 2023. "Forecasting cryptocurrencies volatility using statistical and machine learning methods: A comparative study". Elsevier BV. https://doi.org/10.1016/j.asoc.2023.111132.
[4]Ibrahim, A., Kashef, R., & Corrigan, L. (2021). Predicting market movement direction for bitcoin: A comparison of time series modeling methods. Computers and Electrical Engineering, 89, Article 106905.
[5]Kervanci, I. and Akay, F.. 2020. "Review on Bitcoin Price Prediction Using Machine Learning and Statistical Methods". Sakarya University Journal of Computer and Information Sciences. https://doi.org/10.35377/saucis.03.03.774276.
[6]R. K. Jana, I. Ghosh, and D. Das, "A differential evolution-based regression framework for forecasting Bitcoin price," Annals of Operations Research, vol. 306, no. 1, pp. 295–320, Nov. 2021,https://doi.org/10.1007/s10479-021-04000-8.
[7]S. Lahmiri and S. Bekiros, "Cryptocurrency forecasting with deeplearning chaotic neural networks," Chaos, Solitons & Fractals, vol. 118,pp. 35–40, Jan. 2019, https://doi.org/10.1016/j.chaos.2018.11.014.
[8]Cui, T., Ding, S., Jin, H., & Zhang, Y. (2023). Portfolio constructions in cryptocurrency market: A CVaR-based deep reinforcement learning approach.EconomicModelling,119. doi:10.1016/j.econmod.2022.106078.
[9]Ortu, M., Uras, N., Conversano, C., Bartolucci, S., & Destefanis, G. (2022). On technical trading and social media indicators for cryptocurrency price classification through deep learning. Expert Systems with Applications, 198, 116804. doi:10.1016/j.eswa.2022.116804.
[10]Murray, Kate, Rossi, Andrea, Carraro, Diego, and Visentin, Andrea. 2023. "On Forecasting Cryptocurrency Prices: A Comparison of Machine Learning, Deep Learning, and Ensembles". Multidisciplinary Digital Publishing Institute. https://doi.org/10.3390/forecast5010010.
[11]Dimitriadou, A., & Gregoriou,A. (2023). Predicting Bitcoin Prices Using Machine Learning.Entropy, 25(777).https://doi.org/10.3390/e25050777.
[12]Murray, K., Rossi, A., Carraro,D., & Visentin, A. (2023). OnForecasting Cryptocurrency Prices: A Comparison ofMachine Learning, DeepLearning, and Ensembles.Forecasting, 5, 196–209.https://doi.org/10.3390/forecast5010010.
[13]Seabe, P.L., Moutsinga, C.R.B., & Pindza, E. (2023). Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach. Fractal and Fractional, 7(203).https://doi.org/10.3390/fractalfract7020203.
[14]Mariappan, L.T., Pandian, J.A., Kumar, V.D., Geman, O., Chiuchisan, I., & N˘astase, C. (2023). AForecasting Approach to Cryptocurrency Price Index Using Reinforcement Learning. Applied Sciences, 13(2692). https://doi.org/10.3390/app13042692.
[15]Chen, J. (2023). Analysis of Bitcoin Price Prediction Using Machine Learning. Journal of Risk and Financial Management, 16(51). https://doi.org/10.3390/jrfm16010051.
[16]Basher, S. A., & Sadorsky, P. (2022). Forecasting Bitcoin price direction with random forests: How important are interest rates, inflation, and market volatility? Machine Learning with Applications, 9, 100355. https://doi.org/10.1016/j.mlwa.2022.100355.
[17]Yao, W., Xu, K., & Li, Q. (2019). Exploring the Influence of News Articles on Bitcoin Price with Machine Learning. Proceedings of the 2019 International Conference on Computer Science and Communication Engineering (ICSC), Shenzhen, China.
[18]Passalis, N., Avramelou, L., Seficha, S., Tsantekidis, A., Doropoulos, S., Makris, G., & Tefas, A. (2022).Multisource financial sentiment analysis for detecting Bitcoin price change indications using deep learning. Neural ComputingandApplications, 34, 19441-19452. https://doi.org/10.1007/s00521-022-07509-6.
[19]Lahmiri, S., & Bekiros, S. (2021). Deep Learning Forecasting in Cryptocurrency High-FrequencyTrading. Cognitive Computation, 13, 485–487. https://doi.org/10.1007/s12559-021-09841-w.
[20]Borrageiro, G., Firoozye, N., & Barucca, P. (2022). The Recurrent Reinforcement Learning Crypto Agent. arXiv preprint arXiv:2201.04699.
[21]Jin, C., & Li, Y. (2023). Cryptocurrency Price Prediction Using Frequency Decomposition and Deep Learning. Fractal and Fractional.ttps://doi.org/10.3390/fractalfract7100708.
[22]Khaniki, M.A., & Manthouri, M. (2024). Enhancing Price Prediction in Cryptocurrency Using Transformer Neural Network and Technical Indicators. ArXiv, abs/2403.03606.
[23]Ladhari, A., & Boubaker, H. (2024). Deep Learning Models for Bitcoin Prediction Using Hybrid Approaches with Gradient-Specific Optimization. Forecasting.
[24]Bouslimi, J., Boubaker, S., & Tissaoui, K. (2024). Forecasting of Cryptocurrency Price and Financial Stability: Fresh Insights based on Big Data Analytics and Deep Learning Artificial Intelligence Techniques. Engineering, Technology & Applied Science Research, 14(3), 14162–14169. https://doi.org/10.48084/etasr.7096.
[25]R.Bourday, I.Aatouchi, M.AitKerroum & A.Zaaouat. (2024),”Cryptocurrency Forecasting UsingDeep Learning Models:A Comparative Analysis,”HighTech and Innovation Journal Vol. 5, No.4, December, 2024.Doi: 10.28991/HIJ-2024-05-04-013.
[26]Glenski, M., Weninger, T., & Volkova, S. (2019). Improved Forecasting of Cryptocurrency Price using Social Signals. arXiv preprint arXiv:1907.00558.
[27]Nazmiye Ceren Abay, Cuneyt Gurcan Akcora, Yulia R. Gel, Umar D. Islambekov, Murat Kantarcioglu, Yahui Tian, Bhavani Thuraisingham. ”ChainNet: Learning on Blockchain Graphs with Topological Features.” To Appear in the 2019 IEEE International Conference on Data Mining (ICDM).
[28]Ider, D., & Lessmann, S. (2022). Forecasting Cryptocurrency Returns from Sentiment Signals: An Analysis of BERT Classifiers and Weak Supervision. arXiv preprint arXiv:2204.05781.
[29]Fan Fang, Waichung Chung, Carmine Ventre, Michail Basios, Leslie Kanthan, Lingbo Li, Fan Wu.”Ascertaining price formation in cryptocurrency markets with Deep Learning.” arXiv preprint arXiv:2003.00803.
[30]Frohmann, M., Karner, M., Khudoyan, S., Wagner, R., & Schedl, M. (2023). Predicting the Price of Bitcoin Using Sentiment-Enriched Time Series Forecasting. Big Data and Cognitive Computing, 7(3), 137. https://doi.org/10.3390/bdcc7030137.