Analisis Prediktif Harga Penutupan Harian Bitcoin Menggunakan Arsitektur Jaringan Saraf Tiruan Long Short-Term Memory
-
Suyanti Suyanti
*
Universitas Dinamika Bangsa, Jambi,
Indonesia
- Chandy Ophelia S Universitas Dinamika Bangsa, Jambi, Indonesia
- Lies Aryani Universitas Dinamika Bangsa, Jambi, Indonesia (*) Corresponding Author
Abstract
The highly volatile price of Bitcoin makes it difficult for financial market players. This research aims to build a Bitcoin daily closing price prediction model using Long Short-Term Memory (LSTM) neural network. Bitcoin price data from January 1, 2014 to May 9, 2025 was taken from Yahoo Finance, normalized with MinMaxScaler, and divided into 80% training data and 20% testing data. The LSTM model, which consists of two LSTM layers (50 units each) and two dense layers, was trained with Adam optimization and mean squared error loss function. The model uses the 60-day price sequence to predict the next day's price. The evaluation results show high accuracy with Root Mean Squared Error (RMSE) 105.80, Mean Squared Error (MSE) 2,822,880.74, Mean Absolute Error (MAE) 1,103.42, and R-squared (R²) 0.995. This model becomes one of the reliable prediction tools for financial decisions using historical data. This research enriches machine learning-based bitcoin price prediction solutions.
Downloads
References
K. John, M. O’Hara, and F. Saleh, “Bitcoin and beyond,” Annual Review of Financial Economics, vol. 14, no. 1, pp. 95–115, 2022, doi: https://doi.org/10.1146/annurev-financial-111620-011240.
P. Jaquart, D. Dann, and C. Weinhardt, “Short-term bitcoin market prediction via machine learning,” The Journal of Finance and Data Science, vol. 7, pp. 45–66, Nov. 2021, doi: 10.1016/j.jfds.2021.03.001.
S. Arslan, “Bitcoin Price Prediction Using Sentiment Analysis and Empirical Mode Decomposition,” Computational Economics, vol. 65, no. 4, Art. no. 4, May 2024, doi: 10.1007/s10614-024-10588-3.
R. Hajare, C. Puri, and P. M. Gote, “Bitcoin Price Prediction Using Deep Learning Models,” in 2025 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL), Feb. 2025, pp. 1678–1683. doi: 10.1109/ICSADL65848.2025.10933412.
L. Cocco, R. Tonelli, and M. Marchesi, “Predictions of bitcoin prices through machine learning based frameworks,” PeerJ Computer Science, vol. 7, p. e413, Mar. 2021, doi: 10.7717/peerj-cs.413.
O. Omole and D. Enke, “Deep learning for Bitcoin price direction prediction: models and trading strategies empirically compared,” Financial Innovation, vol. 10, no. 1, p. 117, Aug. 2024, doi: 10.1186/s40854-024-00643-1.
A. M. Khedr, I. Arif, P. R. P V, M. El-Bannany, S. M. Alhashmi, and M. Sreedharan, “Cryptocurrency price prediction using traditional statistical and machine-learning techniques: A survey,” Intelligent Systems in Accounting, Finance and Management, vol. 28, no. 1, pp. 3–34, 2021, doi: 10.1002/isaf.1488.
P. L. Seabe, C. R. B. Moutsinga, and E. Pindza, “Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach,” Fractal and Fractional, vol. 7, no. 2, Art. no. 2, Feb. 2023, doi: 10.3390/fractalfract7020203.
P. Anitha Rajakumari, S. Karthick, S. Gupta, S. Gupta, R. P. Mahapatra, and S. Vinoth Kumar, “Enhancing Bitcoin Price Prediction Using LSTM and GRU Models,” in Proceedings of International Conference on Recent Trends in Computing, R. P. Mahapatra, S. Roy, and P. Parwekar, Eds., Singapore: Springer Nature Singapore, 2025, pp. 177–188.
N. S. Wen and L. S. Ling, “Evaluation of Cryptocurrency Price Prediction Using LSTM and CNNs Models | Wen | JOIV : International Journal on Informatics Visualization,” Nov. 2023, doi: http://dx.doi.org/10.30630/joiv.7.3-2.2344.
I. S. Kervanci, M. F. Akay, E. Özceylan, IT Department, Gaziantep University, Gaziantep, 27300, Turkey, Computer Engineering Department, Çukurova University, Adana, 01250, Turkey, and Industrial Engineering Department, Gaziantep University, Gaziantep, 27300, Turkey, “Bitcoin price prediction using LSTM, GRU and hybrid LSTM-GRU with bayesian optimization, random search, and grid search for the next days,” JIMO, vol. 20, no. 2, pp. 570–588, 2024, doi: 10.3934/jimo.2023091.
J. Cheng, S. Tiwari, D. Khaled, M. Mahendru, and U. Shahzad, “Forecasting Bitcoin prices using artificial intelligence: Combination of ML, SARIMA, and Facebook Prophet models,” Technological Forecasting and Social Change, vol. 198, p. 122938, Jan. 2024, doi: 10.1016/j.techfore.2023.122938.
G. Giyanda and S. Saidah, “Auto Machine Learning dengan Menggunakan H2O AutoML untuk Prediksi Harga Bitcoin: Array,” Jurnal Ilmiah Komputasi, vol. 20, no. 2, Art. no. 2, Jun. 2021.
M. Nirraca and E. Hartati, “Prediksi Harga Bitcoin Menggunakan Metode Long Short Term Memory,” Jurnal Digital Teknologi Informasi, vol. 7, no. 1, Art. no. 1, Mar. 2024, doi: 10.32502/digital.v7i1.7974.
S. Saadah and H. Salsabila, “Prediksi Harga Bitcoin Menggunakan Metode Random Forest: (Studi Kasus: Data Acak Pada Masa Pandemic Covid-19),” Jurnal Komputer Terapan, vol. 7, no. 1, Art. no. 1, May 2021, doi: 10.35143/jkt.v7i1.4618.
J. Julianto, “Analisis Investasi Dalam Memprediksi Pergerakan Harga Bitcoin Dengan Menggunakan Recurrent Neural Network Pada Platform Indodax,” Jurnal Ilmiah Rekayasa dan Manajemen Sistem Informasi, vol. 8, no. 2, Art. no. 2, Sep. 2022, doi: 10.24014/rmsi.v8i2.17233.
M. A. Maliki, I. Cholissodin, and N. Yudistira, “Prediksi Pergerakan Harga Cryptocurrency Bitcoin terhadap Mata Uang Rupiah menggunakan Algoritme LSTM,” J-PTIIK, vol. 6, no. 7, pp. 3259–3268, Aug. 2022.
C. Raj and M. Chattopadhyay, “Bitcoin price prediction using LSTM autoencoder regularized by false nearest neighbor loss,” Soft Computing, vol. 28, no. 21, pp. 12827–12834, Nov. 2024, doi: 10.1007/s00500-024-10301-4.
E. Koo and G. Kim, “Centralized decomposition approach in LSTM for Bitcoin price prediction,” Expert Systems with Applications, vol. 237, p. 121401, Mar. 2024, doi: 10.1016/j.eswa.2023.121401.
W. Abdullah and A. Salah, “A novel hybrid deep learning model for price prediction,” International Journal of Electrical and Computer Engineering, vol. 13, no. 3, pp. 3420–3431, 2023.
W. Lu, J. Li, J. Wang, and L. Qin, “A CNN-BiLSTM-AM method for stock price prediction,” Neural Computing and Applications, vol. 33, no. 10, pp. 4741–4753, May 2021, doi: 10.1007/s00521-020-05532-z.
F. Mehrdoust and M. Noorani, “Prediction of cryptocurrency prices by deep learning models: A case study for Bitcoin and Ethereum,” J. Finan. Eng., vol. 10, no. 04, p. 2350032, Dec. 2023, doi: 10.1142/S2424786323500329.
G. Belalova, S. Mannanova, and B. Karimov, “The Future of Bitcoin Price Predictions Integrating Deep Learning and the Hybrid Model Method,” in Proceedings of the 7th International Conference on Future Networks and Distributed Systems, Dubai United Arab Emirates: ACM, Dec. 2023, pp. 202–211. doi: 10.1145/3644713.3644739.
F. Febriansyah, A. Sujjada, and F. Sembiring, “Prediksi Harga Bitcoin Menggunakan Algoritma Long Short Term Memory (LSTM),” INOVTEK Polbeng - Seri Informatika, vol. 9, no. 1, Art. no. 1, Jun. 2024, doi: 10.35314/isi.v9i1.4247.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Prediktif Harga Penutupan Harian Bitcoin Menggunakan Arsitektur Jaringan Saraf Tiruan Long Short-Term Memory
Pages: 61-68
Copyright (c) 2025 Suyanti Suyanti, Chandy Ophelia S, Lies Aryani
This work is licensed under a Creative Commons Attribution 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 Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment 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 acknowledgment 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 (Refer to The Effect of Open Access).
