Application of CNN-BiLSTM Algorithm for Ethereum Price Prediction
DOI:
https://doi.org/10.30871/jaic.v9i4.9757Keywords:
Ethereum, Price Prediction, CNN-BiLSTMAbstract
The volatile and dynamic Ethereum (ETH) market demands an accurate predictive model to support investment decision making. The complexity of ETH time series data and the influence of various external factors make price prediction a challenge in itself. This study aims to develop an ETH price prediction model using a combined architecture of Convolutional Neural Network (CNN) and also Bidirectional Long Short-Term Memory (BiLSTM). CNN is used to extract local features from historical ETH closing price data, while BiLSTM models bidirectional temporal patterns. The dataset used includes ETH daily price from January 2020 to January 2025, which are obtained from Yahoo Finance and have gone through a normalization process and transformation into sequential form. The model is trained for 100 epochs with an early stopping mechanism to prevent overfitting and evaluated using the MAPE and coefficient of determination (R²) metrics. The evaluation results show that the CNN-BiLSTM model is able to predict ETH prices with a MAPE value of 2.8546% and an R² of 0.9415, indicating high performance in capturing actual data trends. This study shows that the hybrid CNN-BiLSTM approach is effective for Ethereum price prediction.
Downloads
References
[1] O. L. D. Warsito and R. Robiyanto, “Analisis Volatilitas Cryptocurrency, Emas, Dollar, Dan Indeks Harga Saham (Ihsg),” Int. J. Soc. Sci. Bus., vol. 4, no. 1, pp. 40–46, 2020, doi: 10.23887/ijssb.v4i1.23887.
[2] F. A. Ramadhan and N. D. Nathasia, “Prediksi Harga Dan Kinerja Aset Bitcoin Menggunakan Algoritma Long Short-Term Memory,” vol. 15, no. 1, pp. 68–76, 2025.
[3] P. H. Setianingrum and D. Prastuti, “The impact of macroeconomics and financial variables on sectors’ index in Indonesia stock exchange market,” Int. J. Econ. Res., vol. 14, no. 17, pp. 41–49, 2017.
[4] Q. Yang, Y. Sun, and Y. Wu, “Bitcoin Price Prediction Based on CNN-Bi-LSTM-Attention Model,” Highlights Business, Econ. Manag., vol. 16, pp. 80–86, 2023, doi: 10.54097/hbem.v16i.10540.
[5] A. Staffini, “A CNN–BiLSTM Architecture for Macroeconomic Time Series Forecasting,” Eng. Proc., vol. 39, no. 1, 2023, doi: 10.3390/engproc2023039033.
[6] M. J. Hamayel and A. Y. Owda, “A Novel Cryptocurrency Price Prediction Model Using GRU, LSTM and bi-LSTM Machine Learning Algorithms,” AI, vol. 2, no. 4, pp. 477–496, 2021, doi: 10.3390/ai2040030.
[7] A. R. F. Dewandra, A. P. Wibawa, U. Pujianto, A. B. P. Utama, and A. Nafalski, “Journal Unique Visitors Forecasting Based on Multivariate Attributes Using CNN,” Int. J. Artif. Intell. Res., vol. 6, no. 2, 2022, doi: 10.29099/ijair.v6i1.274.
[8] S. Indolia, A. K. Goswami, S. P. Mishra, and P. Asopa, “Conceptual Understanding of Convolutional Neural Network- A Deep Learning Approach,” Procedia Comput. Sci., vol. 132, pp. 679–688, 2018, doi: 10.1016/j.procs.2018.05.069.
[9] D. M. Gunarto, S. Sa’adah, and D. Q. Utama, “Predicting Cryptocurrency Price Using RNN and LSTM Method,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 12, no. 1, pp. 1–8, 2023, doi: 10.32736/sisfokom.v12i1.1554.
[10] S. H. Permatasari, I. M. Nur, and F. Fauzi, “Metode Bidirectional Long Short-Term Memory (BiLSTM) Untuk Memprediksi Harga Saham BBRI Dengan Optimasi Nesterov Adaptive Moment (Nadam),” pp. 1151–1159.
[11] H. Awarulloh, D. F. Shiddieq, and D. Nurhayati, “Penggunaan Multivariat Model Bidirectional LSTM untuk Prediksi Cuaca : Optimalisasi Waktu Tanam Padi Petani Kabupaten Garut,” no. 1, pp. 127–138, 2025.
[12] M. Mushliha, “Implementasi CNN-BiLSTM untuk Prediksi Harga Saham Bank Syariah di Indonesia,” Jambura J. Math., vol. 6, no. 2, pp. 195–203, 2024, doi: 10.37905/jjom.v6i2.26509.
[13] J. Zhang, L. Ye, and Y. Lai, “Stock Price Prediction Using CNN-BiLSTM-Attention Model,” pp. 1–18, 2023.
[14] S. Kim and H. Kim, “A new metric of absolute percentage error for intermittent demand forecasts,” Int. J. Forecast., vol. 32, no. 3, pp. 669–679, 2016, doi: 10.1016/j.ijforecast.2015.12.003.
[15] J. Gao, “R-Squared (R2) – How much variation is explained?” Res. Methods Med. Heal. Sci., vol. 5, no. 4, pp. 104–109, 2024, doi: 10.1177/26320843231186398.
[16] Chainalysis, “The 2024 Geography of Crypto Report,” 2024.
[17] D. Gunawan and I. Febrianti, “Ethereum Value Forecasting Model using Autoregressive Integrated Moving Average (ARIMA),” Int. J. Adv. Soc. Sci. Humanit., vol. 2, no. 1, pp. 29–35, 2023, doi: 10.56225/ijassh.v2i1.151.
[18] D. Xu, “Price Prediction of Cryptocurrency based on LSTM Model: Evidence from Ethereum,” Highlights Sci. Eng. Technol., vol. 39, pp. 744–748, 2023, doi: 10.54097/hset.v39i.6639.
[19] M. Saputra, “Comparative Analysis of LSTM and GRU Models for Ethereum (ETH) Price Prediction,” Int. J. Business, Econ. Soc. Dev., vol. 6, pp. 132–132, 2025.
[20] E. Mahdi, C. Martin-Barreiro, and X. Cabezas, “A Novel Hybrid Approach Using an Attention-Based Transformer + GRU Model for Predicting Cryptocurrency Prices,” Mathematics, vol. 13, no. 9, pp. 1–24, 2025, doi: 10.3390/math13091484.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Hakam Dzakwan Diash, Vannesa Nathania, Mohammad Idhom, Trimono Trimono
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 License (Attribution-ShareAlike 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).
