Ethereum Gas Fee Prediction Using LSTM's Bi-Directional Algorithm
Kata Kunci:
Ethereum, Gas Fee, Bi-LSTM, Deep Learning, Time Series PredictionAbstrak
The Ethereum ecosystem is synonymous with high volatility dynamics, not only in the exchange rate of its assets but also in the transaction fees (gas fees). Because of these uncertainties, proper cost estimation is essential for transaction efficiency. In this study, the Bi-Directional Long Short-Term Memory (Bi-LSTM) algorithm is suggested to be used to model Ethereum's gas fee predictions. The Bi-LSTM architecture was chosen because of its advantages in processing sequential information from two directions (forward and backward). Thus, this architecture makes it possible to map the dependencies of complex long-term patterns more comprehensively compared to one-way models. Data is processed through the normalization and restructuring stages of the sliding window using hourly resolution on-chain datasets collected from Etherscan over a period of one year. The results of the performance evaluation showed that the model was quite responsive in following the trend of gas cost movements, as shown by the Root Mean Squared Error (RMSE) value of 9.3517 Gwei and Mean Absolute Error (MAE) of 3.7893 Gwei. However, a Mean Absolute Percentage Error (MAPE) value of 20% was obtained, which suggests that the model still struggles to anticipate extreme price spike anomalies, also known as spikes. Overall, the study concludes that Bi-LSTM has significant potential for blockchain time series data analysis; However, in order to handle the highly volatile characteristics of the market, this method needs to be further optimized.
Unduhan
Referensi
[1] T. B. Sianturi, I. Cholissodin, and N. Yudistira, “Penerapan Algoritma Long Short-Term Memory (LSTM) berbasis Multi Fungsi Aktivasi Terbobot dalam Prediksi Harga Ethereum,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 7, no. 3, pp. 1101–1107, 2023
[2] R. Parlika and B. Rahmat, “Minimum, Maximum, and Average Implementation of Patterned Datasets in Mapping Cryptocurrency Fluctuation Patterns,” INTERNATIONAL JOURNAL ON INFORMATICS VISUALIZATION (JOIV), vol. 8, pp. 378–386, Mar. 2024
[3] A. Laurent, L. Brotcorne, and B. Fortz, “Transactions fees optimization in the Ethereum blockchain,” Blockchain: Research and Applications, 2022.
[4] R. Kaur et al., “Development of a cryptocurrency price prediction model: leveraging GRU and LSTM for Bitcoin, Litecoin and Ethereum,” PeerJ Comput Sci, 2025.
[5] V. Tyshchenko, S. Achkasova, O. Naidenko, S. Kanyhin, and V. Karpova, “Development of recurrent neural networks for price forecasting at cryptocurrency exchanges,” Eastern-European Journal of Enterprise Technologies, 2023.
[6] A. Ferenczi and C. Bădică, “Prediction of Ethereum gas prices using DeepAR and probabilistic forecasting,” Journal of Information and Telecommunication, 2023.
[7] R. Mars, A. Abid, S. Cheikhrouhou, and S. Kallel, “A Machine Learning Approach for Gas Price Prediction in Ethereum Blockchain,” in 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), 2021.
[8] C. Butler and M. Crane, “Blockchain Transaction Fee Forecasting: A Comparison of Machine Learning Methods,” ArXiv, 2023.
[9] X. Li, Q. Liu, and Y. Wu, “Prediction on blockchain virtual currency transaction under long short-term memory model and deep belief network,” Appl. Soft Comput., 2021.
[10] P. L. Seabe, C. Moutsinga, and E. Pindza, “Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach,” Fractal and Fractional, 2023.
[11] M. J. Hamayel and A. Y. Owda, “A Novel Cryptocurrency Price Prediction Model Using GRU, LSTM and bi-LSTM Machine Learning Algorithms,” AI, 2021.
[12] N. Jagannath et al., “An On-Chain Analysis-Based Approach to Predict Ethereum Prices,” IEEE Access, 2021.
[13] D. Reijsbergen, S. Sridhar, B. Monnot, S. Leonardos, S. Skoulakis, and G. Piliouras, “Transaction Fees on a Honeymoon: Ethereum’s EIP-1559 One Month Later,” Apr. 2022, [Online]. Available: http://arxiv.org/abs/2110.04753
[14] S. Hansun, A. Wicaksana, and A. Q. M. Khaliq, “Multivariate cryptocurrency prediction: comparative analysis of three recurrent neural networks approaches,” J Big Data, 2022.
[15] S. M. Raju and A. M. Tarif, “Real-Time Prediction of BITCOIN Price using Machine Learning Techniques and Public Sentiment Analysis.”
[16] M. Rafi, Q. Mirza, M. I. Sohail, M. L. Aliasghar, A. Aziz, and S. Hameed, “Enhancing Cryptocurrency Price Forecasting Accuracy: A Feature Selection and Weighting Approach With Bi-Directional LSTM and Trend-Preserving Model Bias Correction,” IEEE Access, 2022.
[17] M. F. Bin Hossain, L. Z. Lamia, M. M. Rahman, and Md. M. Khan, “FinBERT-BiLSTM: A Deep Learning Model for Predicting Volatile Cryptocurrency Market Prices Using Market Sentiment Dynamics,” ArXiv, 2024.
[18] N. Srivastava, G. Hinton, A. Krizhevsky, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” 2014.
[19] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Jan. 2017, [Online]. Available: http://arxiv.org/abs/1412.6980
[20] H. Dzakwan Diash, V. Nathania, and M. Idhom, “Application of CNN-BiLSTM Algorithm for Ethereum Price Prediction,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[21] K. Murray, A. Rossi, D. Carraro, and A. Visentin, “On Forecasting Cryptocurrency Prices: A Comparison of Machine Learning, Deep Learning, and Ensembles,” Forecasting, 2023.
[22] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput Sci, vol. 7, pp. 1–24, 2021, doi: 10.7717/PEERJ-CS.623.
[23] K. Murray, A. Rossi, D. Carraro, and A. Visentin, “On Forecasting Cryptocurrency Prices: A Comparison of Machine Learning, Deep Learning, and Ensembles,” Forecasting, 2023.
[24] C. Jin and Y. Li, “Cryptocurrency Price Prediction Using Frequency Decomposition and Deep Learning,” Fractal and Fractional, 2023.
[25] D. Lan, H. Wang, C. Yin, L. Zhou, C. Ge, and X. Lu, Gas Price Prediction Based on Machine Learning Combined with Ethereum Mempool. 2022. doi: 10.1109/MASS56207.2022.00057.
[26] I. P. B. Priadinata, I. G. I. Sudipa, N. P. S. Meinarni, I. M. L. Radhitya, and I. K. D. G. Supartha, “Comparative Analysis of LSTM, GRU, and Bi-LSTM Deep Learning Models for Time Series Cryptocurrency Price Forecasting,” sinkron, vol. 9, no. 3, pp. 1024–1035, Jul. 2025, doi: 10.33395/sinkron.v9i3.14795.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Rizky Parlika, Irohito Nozomi, Muhamad Faizhal Musthafa
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
