Email this article 
Optimizing Bitcoin Price Prediction with LSTM: A Comprehensive Study on Feature Engineering and the April 2024 Halving Impact
Abstract
This research aims to develop a Bitcoin price prediction model using machine learning techniques, with a specific focus on Long Short-Term Memory (LSTM) neural networks. The Bitcoin market is characterized by unique features such as high volatility and the influence of various external factors, which differ significantly from traditional financial markets. As such, precise feature engineering is crucial for accurately modelling Bitcoin prices. Utilizing historical Bitcoin price data from 2014 to 2023, this study extensively evaluates LSTM models. The results indicate that LSTM models provide highly accurate predictions, with a Mean Squared Error (MSE) of 0.0001798 and a Mean Absolute Error (MAE) of 0.0101322. These results demonstrate that LSTM effectively captures the complex and dynamic patterns of Bitcoin prices, outperforming other methods. The findings have significant implications for financial market analysis, especially within the rapidly evolving domain of crypto assets. By leveraging machine learning methodologies, this research enhances understanding of the complexities of the crypto market and offers potential strategies for smarter investment decisions. The success of the LSTM model in improving Bitcoin price prediction accuracy underscores its importance in navigating the volatile and dynamic nature of the crypto market. Overall, this study highlights the substantial potential of machine learning approaches, particularly LSTM models, in analyzing and predicting crypto market behavior. It contributes to the growing academic discourse on the application of advanced technologies in finance and can stimulate further discussions on how machine learning can address challenges and opportunities in the crypto market.
Keywords
Full Text:
PDFReferences
M. Yahya, J. M. Parenreng, and A. Wahid, “A Machine Learning Model for Local Market Prediction Using RFM Model,” vol. 9, no. 1, pp. 24–37, 2024.
S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997, doi: 10.1162/neco.1997.9.8.1735.
Jeremiah Olawumi Arowoogun, Oloruntoba Babawarun, Rawlings Chidi, Adekunle Oyeyemi Adeniyi, and Chioma Anthonia Okolo, “A comprehensive review of data analytics in healthcare management: Leveraging big data for decision-making,” World J. Adv. Res. Rev., vol. 21, no. 2, pp. 1810–1821, 2024, doi: 10.30574/wjarr.2024.21.2.0590.
H. Dehghan Shoorkand, M. Nourelfath, and A. Hajji, “A hybrid CNN-LSTM model for joint optimization of production and imperfect predictive maintenance planning,” Reliab. Eng. Syst. Saf., vol. 241, no. September 2023, 2024, doi: 10.1016/j.ress.2023.109707.
Agus Triyadi, Adi Suwondo, Dian Asmarajati, Nur Hasanah, and Muhamad Fuat Asnawi, “Prediksi Harga Bawang Merah Kering Di Wonosobo Menggunakan Metode Long Short Term Memory,” STORAGE J. Ilm. Tek. dan Ilmu Komput., vol. 3, no. 2, pp. 133–138, 2024, doi: 10.55123/storage.v3i2.3601.
B. Haslhofer, R. Karl, and E. Filtz, “O Bitcoin where art thou? Insight into large-scale transaction graphs,” CEUR Workshop Proc., vol. 1695, pp. 1–4, 2016.
G. Di Battista, V. Di Donato, M. Patrignani, M. Pizzonia, V. Roselli, and R. Tamassia, “Bitconeview: Visualization of flows in the bitcoin transaction graph,” 2015 IEEE Symp. Vis. Cyber Secur. VizSec 2015, pp. 1–8, 2015, doi: 10.1109/VIZSEC.2015.7312773.
D. T. Hermanto, A. Setyanto, and E. T. Luthfi, “Algoritma LSTM-CNN untuk Binary Klasifikasi dengan Word2vec pada Media Online,” Creat. Inf. Technol. J., vol. 8, no. 1, p. 64, 2021, doi: 10.24076/citec.2021v8i1.264.
Y. H. Muáafii, “Optimizing " Open Data Jawa Tengah " through Technology Acceptance Model ( TAM ),” vol. 9, no. 1, pp. 11–23, 2024.
Mustafa Ayobami Raji, Hameedat Bukola Olodo, Timothy Tolulope Oke, Wilhelmina Afua Addy, Onyeka Chrisanctus Ofodile, and Adedoyin Tolulope Oyewole, “Real-time data analytics in retail: A review of USA and global practices,” GSC Adv. Res. Rev., vol. 18, no. 3, pp. 059–065, 2024, [Online]. Available: https://gsconlinepress.com/journals/gscarr/content/real-time-data-analytics-retail-review-usa-and-global-practices
I. C. Azhari and T. Haryanto, “Modeling Of Hyperparameter Tuned RNN-LSTM and Deep Learning For Garlic Price Forecasting In Indonesia,” J. Informatics Telecommun. Eng., vol. 7, no. 2, pp. 502–513, 2024, doi: 10.31289/jite.v7i2.10714.
G. Ding and L. Qin, “Study on the prediction of stock price based on the associated network model of LSTM,” Int. J. Mach. Learn. Cybern., vol. 11, no. 6, pp. 1307–1317, 2020, doi: 10.1007/s13042-019-01041-1.
H. Naveed, S. Anwar, M. Hayat, K. Javed, and A. Mian, “Survey: Image mixing and deleting for data augmentation,” Eng. Appl. Artif. Intell., vol. 131, no. December 2023, p. 107791, 2024, doi: 10.1016/j.engappai.2023.107791.
N. Shi Wen and L. Sook Ling, “Evaluation of Cryptocurrency Price Prediction Using LSTM and CNNs Models,” Int. J. Informatics Vis., vol. 7, no. 3–2, pp. 2016–2024, 2023.
P. Jay, V. Kalariya, P. Parmar, S. Tanwar, N. Kumar, and M. Alazab, “Stochastic neural networks for cryptocurrency price prediction,” IEEE Access, vol. 8, pp. 82804–82818, 2020, doi: 10.1109/ACCESS.2020.2990659.
E. Akyildirim, A. Goncu, and A. Sensoy, “Prediction of cryptocurrency returns using machine learning,” Ann. Oper. Res., vol. 297, no. 1–2, pp. 3–36, 2021, doi: 10.1007/s10479-020-03575-y.
M. Liu, G. Li, J. Li, X. Zhu, and Y. Yao, “Forecasting the price of Bitcoin using deep learning,” Financ. Res. Lett., vol. 40, no. April 2020, p. 101755, 2021, doi: 10.1016/j.frl.2020.101755.
B. B. Sahoo, R. Jha, A. Singh, and D. Kumar, “Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting,” Acta Geophys., vol. 67, no. 5, pp. 1471–1481, 2019, doi: 10.1007/s11600-019-00330-1.
E. Verianto, “MENCEGAH OVERFITTING PADA MODEL PREDIKSI,” vol. 9, no. 2, pp. 195–204, 2024.
A. Caliciotti, M. Corazza, and G. Fasano, “From regression models to machine learning approaches for long term Bitcoin price forecast,” Ann. Oper. Res., vol. 336, no. 1–2, pp. 359–381, 2024, doi: 10.1007/s10479-023-05444-w.
S. Park and J. S. Yang, “Machine learning models based on bubble analysis for Bitcoin market crash prediction,” Eng. Appl. Artif. Intell., vol. 135, no. April 2023, p. 108857, 2024, doi: 10.1016/j.engappai.2024.108857.
I. A. Pradana, A. D. Rahajoe, and A. N. Sihananto, “JALAN BERBASIS ANDROID DENGAN IMPLEMENTASI ALGORITMA HYBRID CNN-LSTM,” vol. 5, no. 2, pp. 1–10, 2024.
P. Algoritma, G. Untuk, M. Optimasi, K. Jalur, T. Dalam, and K. Travelling, “Jurnal Teknologi Terpadu PROBLEM,” J. Teknol. Terpadu Vol, vol. 7, no. 2, pp. 77–82, 2021, [Online]. Available: https://journal.nurulfikri.ac.id/index.php/jtt/article/download/318/201
F. Karim, S. Majumdar, H. Darabi, and S. Chen, “LSTM Fully Convolutional Networks for Time Series Classification,” IEEE Access, vol. 6, pp. 1662–1669, 2017, doi: 10.1109/ACCESS.2017.2779939.
L. Zaman, S. Sumpeno, and M. Hariadi, “Analisis Kinerja LSTM dan GRU sebagai Model Generatif untuk Tari Remo,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 8, no. 2, p. 142, 2019, doi: 10.22146/jnteti.v8i2.503.
X. Song et al., “Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model,” J. Pet. Sci. Eng., vol. 186, no. July 2019, p. 106682, 2020, doi: 10.1016/j.petrol.2019.106682.
J. Guo, Z. Lao, M. Hou, C. Li, and S. Zhang, “Mechanical fault time series prediction by using EFMSAE-LSTM neural network,” Meas. J. Int. Meas. Confed., vol. 173, no. October 2020, p. 108566, 2021, doi: 10.1016/j.measurement.2020.108566.
R. C. Staudemeyer and E. R. Morris, “Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks,” pp. 1–42, 2019, [Online]. Available: http://arxiv.org/abs/1909.09586
DOI: https://doi.org/10.21831/elinvo.v9i1.72518
Refbacks
- There are currently no refbacks.
Copyright (c) 2024 Elinvo (Electronics, Informatics, and Vocational Education)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Our Journal indexed by:
ISSN 2477-2399 (online) || ISSN 2580-6424 (print)
