Hybrid Autoencoder Architectures with LSTM and GRU Layers for Bitcoin Price Prediction
Downloads
The high volatility of cryptocurrency markets, particularly Bitcoin, poses significant challenges for accurate price forecasting. To address this issue, this study evaluates the performance of four autoencoder-based deep learning architectures: AE-LSTM, AE-GRU, AE-LSTM-GRU, and AE-GRU-LSTM. The models were developed and tested using a univariate approach, where only the closing price was used as input, and two different window sizes (30 and 60) were applied to analyse the effect of historical sequence length on prediction accuracy. Several parameter configurations, including the number of epochs, dropout rate, and learning rate, were explored to determine the optimal model performance. The dataset comprises Bitcoin’s daily closing prices from 2018 to 2025, encompassing diverse market phases, including both bullish and bearish trends. Model performance was assessed using four evaluation metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), the coefficient of determination (R²), and Mean Absolute Percentage Error (MAPE). The results indicate that the AE-LSTM-GRU consistently achieved the best overall performance across all configurations. For a window size of 30, it achieved an RMSE of 1.53067 and a MAPE of 1.98%, while for a window size of 60, the best performance recorded was an RMSE of 1.55217 and a MAPE of 2.09%. The hybrid structure combining LSTM’s capability to capture long-term dependencies with GRU’s efficiency in information decoding demonstrated strong robustness in modelling highly volatile time series. This study contributes to financial time series forecasting by presenting hybrid autoencoder architectures that strike a balance between predictive accuracy and computational efficiency, providing practical insights for researchers and practitioners in financial technology and cryptocurrency analytics
[1] V. Akila, M. V. S. Nitin, I. Prasanth, S. Reddy M, and G. Akash Kumar, “A Cryptocurrency Price Prediction Model using Deep Learning,” E3S Web of Conferences, vol. 391, 2023, doi: 10.1051/e3sconf/202339101112.
[2] R. Shirwaikar et al., “Optimized Deep Learning Framework for Cryptocurrency Price Prediction,” SN Comput Sci, vol. 6, no. 1, 2025, doi: 10.1007/s42979-024-03611-9.
[3] M. J. Hamayel and A. Y. Owda, “A Novel Cryptocurrency Price Prediction Model Using GRU, LSTM and bi-LSTM Machine Learning Algorithms,” AI (Switzerland), vol. 2, no. 4, pp. 477–496, 2021, doi: 10.3390/ai2040030.
[4] M. Melina et al., “Cryptocurrency Time Series Forecasting Model Using Gru Algorithm Based on Machine Learning,” Barekeng, vol. 19, no. 2, pp. 1317–1328, 2025, doi: 10.30598/barekengvol19iss2pp1317-1328.
[5] P. Boozary, S. Sheykhan, and H. GhorbanTanhaei, “Forecasting the Bitcoin price using the various Machine Learning: A systematic review in data-driven marketing,” Systems and Soft Computing, vol. 7, no. August 2024, p. 200209, 2025, doi: 10.1016/j.sasc.2025.200209.
[6] V. Karnati, L. D. Kanna, T. N. Pandey, and C. K. Nayak, “Prediction and Analysis of Bitcoin Price using Machine learning and Deep learning models,” EAI Endorsed Transactions on Internet of Things, vol. 10, pp. 1–8, 2024, doi: 10.4108/eetiot.5379.
[7] R. Kaur et al., “Development of a cryptocurrency price prediction model: leveraging GRU and LSTM for Bitcoin, Litecoin and Ethereum,” PeerJ Comput Sci, vol. 11, pp. 1–30, 2025, doi: 10.7717/peerj-cs.2675.
[8] I. A. K. Shaikh, P. V. Krishna, S. G. Biswal, A. S. Kumar, S. Baranidharan, and K. Singh, “Bayesian Optimization with Stacked Sparse Autoencoder based Cryptocurrency Price Prediction Model,” Proceedings - 5th International Conference on Smart Systems and Inventive Technology, ICSSIT 2023, no. March, pp. 653–658, 2023, doi: 10.1109/ICSSIT55814.2023.10061153.
[9] A. Viéitez, M. Santos, and R. Naranjo, “Machine learning Ethereum cryptocurrency prediction and knowledge-based investment strategies,” Knowl Based Syst, vol. 299, no. March, 2024, doi: 10.1016/j.knosys.2024.112088.
[10] S. Syed, S. M. Talha, A. Iqbal, N. Ahmad, and M. A. Alshara, “Seeing Beyond Noise: Improving Cryptocurrency Forecasting with Linear Bias Correction,” AI (Switzerland), vol. 5, no. 4, pp. 2829–2851, 2024, doi: 10.3390/ai5040136.
[11] A. Ladhari and H. Boubaker, “Deep Learning Models for Bitcoin Prediction Using Hybrid Approaches with Gradient-Specific Optimization,” Forecasting, vol. 6, no. 2, pp. 279–295, 2024, doi: 10.3390/forecast6020016.
[12] P. L. Seabe, C. R. B. Moutsinga, and E. Pindza, “Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach,” pp. 1–18, 2023, doi: 10.3390/fractalfract7020203.
[13] M. C. Lee, “Bitcoin Trend Prediction with Attention-Based Deep Learning Models and Technical Indicators,” Systems, vol. 12, no. 11, 2024, doi: 10.3390/systems12110498.
[14] P. Satria and T. Putra Purnama, “Bitcoin Price Prediction Using LSTM Model: April 2024 Halving Case Study,” vol. 6424, no. April, pp. 2580–6424, 2024, doi: 10.21831/elinvo.v9i1.72518.
[15] N. Tripathy et al., “Bitcoin volatility forecasting: a comparative analysis of conventional econometric models with deep learning models,” International Journal of Electrical and Computer Engineering, vol. 15, no. 1, pp. 614–623, 2025, doi: 10.11591/ijece.v15i1.pp614-623.
[16] S. Ranjan, P. Kayal, and M. Saraf, “Bitcoin Price Prediction: A Machine Learning Sample Dimension Approach,” Comput Econ, vol. 61, no. 4, pp. 1617–1636, 2023, doi: 10.1007/s10614-022-10262-6.
[17] I. Akouaouch and A. Bouayad, “A new deep learning approach for predicting high-frequency short-term cryptocurrency price,” Bulletin of Electrical Engineering and Informatics, vol. 14, no. 1, pp. 513–523, 2025, doi: 10.11591/eei.v14i1.7377.
[18] S. Sujana and B. G. Jairam, “Machine Learning based Framework to Predict the Bitcoin Price,” 15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024, vol. 1, pp. 1228–1235, 2024.
[19] S. E. Parameswaran, V. Ramachandran, and S. Shukla, “Crypto Trend Prediction Based on Wavelet Transform and Deep Learning Algorithm,” Procedia Comput Sci, vol. 235, pp. 1179–1189, 2024, doi: 10.1016/j.procs.2024.04.112.
[20] H. M. Fadhil and N. Q. Makhool, “Forecasting Cryptocurrency Market Trends with Machine Learning and Deep Learning,” BIO Web Conf, vol. 97, no. April, 2024, doi: 10.1051/bioconf/20249700053.
[21] M. YURTSEVER, “Gold Price Forecasting Using LSTM, Bi-LSTM and GRU,” European Journal of Science and Technology, no. January, 2021, doi: 10.31590/ejosat.959405.
[22] K. Ateeq, A. A. Al Zarooni, A. Rehman, and M. A. Khan, “A Mechanism for Bitcoin Price Forecasting using Deep Learning,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 8, pp. 441–448, 2023, doi: 10.14569/IJACSA.2023.0140849.
[23] D. M. Gunarto, S. Sa’adah, and D. Q. Utama, “Predicting Cryptocurrency Price Using RNN and LSTM Method,” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 12, no. 1, pp. 1–8, 2023, doi: 10.32736/sisfokom.v12i1.1554.
[24] A. Yanimaharta and H. A. Santoso, “Performance Evaluation of Deep Learning Models for Cryptocurrency Price Prediction using LSTM, GRU, and Bi-LSTM,” International Journal of Systematic Innovation, vol. 8, no. 1, pp. 49–62, 2025, doi: 10.6977/IJoSI.202403_8(1).0005.
[25] C. Raj and M. Chattopadhyay, “Bitcoin Price Prediction using LSTM Autoencoder Regularized by False Nearest Neighbor Loss,” Chahatraj.Github.Io, no. October 2020, pp. 12827–12834, 2024, doi: 10.1007/s00500-024-10301-4.
[26] N. P. N. P. Dewi, L. Yungho, K. Mustofa, and M. Riasetiawan, “ENHANCING DIESEL BACKUP POWER FORECASTING WITH LSTM , GRU , AND AUTOENCODER-BASED INPUT ENCODING,” vol. 14, no. 1, pp. 183–199, 2025, doi: 10.23887/janapati.v14i1.92079.
[27] J. Dip Das, R. K. Thulasiram, C. Henry, and A. Thavaneswaran, “Encoder–Decoder Based LSTM and GRU Architectures for Stocks and Cryptocurrency Prediction,” Journal of Risk and Financial Management, vol. 17, no. 5, 2024, doi: 10.3390/jrfm17050200.
[28] L. Li, A. Arab, J. Liu, J. Liu, and Z. Han, “Bitcoin options pricing using LSTM-Based prediction model and blockchain statistics,” Proceedings - 2019 2nd IEEE International Conference on Blockchain, Blockchain 2019, pp. 67–74, 2019, doi: 10.1109/Blockchain.2019.00018.
[29] M. P. A. Saputra, R. A. Ibrahim, and R. S. Saputra, “Comparative Analysis of LSTM and GRU Models for Ethereum (ETH) Price Prediction,” Lecture Notes in Electrical Engineering, vol. 968, no. 1, pp. 399–410, 2025, doi: 10.1007/978-981-19-7346-8_34.
[30] M. H. Abdul Hadi, N. A. Ramli, and Q. UI Islam, “Predicting Bitcoin and Ethereum prices using long short-term memory and gated recurrent unit,” Data Analytics and Applied Mathematics (DAAM), no. September 2023, pp. 8–17, 2023, doi: 10.15282/daam.v4i2.10195.
[31] R. M. L. G, N. Selby, and A. Taparia, “An Efficient Stock Price Prediction Mechanism Using Multivariate Sequential LSTM Autoencoder,” pp. 0–19, 2023, doi: 10.21203/rs.3.rs-2599921/v1.
[32] M. Iqbal, A. Iqbal, A. Alshammari, I. Ali, L. A. Maghrabi, and N. Usman, “Sell or HODL Cryptos: Cryptocurrency Short-to-Long Term Projection Using Simultaneous Classification-Regression Deep Learning Framework,” IEEE Access, vol. 12, pp. 118169–118184, 2024, doi: 10.1109/ACCESS.2024.3448234.
[33] T. Awoke, M. Rout, L. Mohanty, and S. C. Satapathy, Bitcoin Price Prediction and Analysis Using Deep Learning Models, vol. 134, no. February 2021. Springer Singapore, 2021. doi: 10.1007/978-981-15-5397-4_63.
Copyright (c) 2025 Yuni Yamasari, Nurun Nafisah, Ervin Yohannes (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-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-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 work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
