Optimising Bitcoin Price Forecasting Using Lstm, Gru, Prophet, Var, And Es Multi-Model Approaches

Authors

  • Anggito Karta Wijaya Information Systems Department, Faculty of Computer Science, University of Jember, Indonesia
  • Amalan Fadil Gaib Industrial Engineering Department, Faculty of Engineering, State University of Gorontalo, Indonesia
  • I Gusti Ngurah Bagus Ferry Mahayudha Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University, Indonesia
  • Nurul Andini Information Systems and Technology Departement, Faculty of Engineering, State University of Jakarta, Indonesia
  • Tegar Fadillah Zanestri Informatics Engineering, Faculty of Engineering, Telkom University, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2025.6.3.4078

Keywords:

Forecasting, Bitcoin, GRU, ES, LSTM, Prophet, Risk Analysis, VaR

Abstract

This study aims to optimize Bitcoin price forecasting by integrating several multi-model approaches, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Prophet, as well as risk analysis using Value at Risk (VaR) and Expected Shortfall (ES). The daily Bitcoin price data from the period of July 17, 2010, to June 28, 2024, obtained from Kaggle, were analyzed using accuracy metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), as they provide a more objective and reliable evaluation of prediction effectiveness. The results show that the LSTM model performed the best, with an MSE of 535,419.12, RMSE of 731.72, MAE of 310.72, and MAPE of 159.01. The GRU model produced similar evaluation values with an MSE of 558,868.06 and RMSE of 747.57. In contrast, Prophet demonstrated lower performance, with an MSE of 59,309,927.76 and RMSE of 7,701.29. The risk analysis indicated that at a 95% confidence level, VaR reached 61,676.43, while ES reached 61,737.58, reflecting additional risk in extreme conditions. This study provides valuable insights into the advantages of the LSTM and GRU models for Bitcoin price forecasting, while also emphasizing the importance of risk analysis in supporting cryptocurrency investment decisions.

Downloads

Download data is not yet available.

References

S. Nakamoto, "Bitcoin: A Peer-to-Peer Electronic Cash System," 2009. [Online]. Tersedia: https://bitcoin.org/bitcoin.pdf.

Bank Indonesia, "Navigating The Architecture of Digital Rupiah," 2022. [Online]. Tersedia: https://www.bi.go.id/en/rupiah/digital-rupiah/Documents/White-Paper-CBDC-2022_en.pdf.

E. H. Kusnadi, R. R. Nasir, dan H. Hulwanullah, "Legal Aspects of Crypto Assets on Indonesian Digital Investment Development," J. Hukum Islam, vol. 12, no. 2, hlm. 145-162, 2023. DOI: https://doi.org/10.14421/sh.v12i2.3168.

E. R. Arminanto dan K. A. Firmansyah, "Bitcoin’s Position in Indonesian Currency Law," Indonesian J. Econ. Finance, vol. 5, no. 2, hlm. 67-78, 2022. DOI: https://doi.org/10.15294/islrev.v5i2.47491.

B. Gülmez, "Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm," Expert Syst. Appl., vol. 227, no. 120346, hlm. 1-15, 2023. DOI: https://doi.org/10.1016/j.eswa.2023.120346.

N. M. Salih dan A. M. Abdulazeez, "Bitcoin Price Prediction Using Hybrid LSTM-GRU Models," Indonesian J. Comput. Sci., vol. 13, no. 1, hlm. 94-101, 2024. DOI: https://doi.org/10.33022/ijcs.v13i1.3725

N. Tripathy, S. Hota, dan D. Mishra, "Performance analysis of bitcoin forecasting using deep learning techniques," Indonesia J. Elect. Eng. Comput. Sci., vol. 31, no. 3, hlm. 1515-1522, Sept. 2023. DOI: https://doi.org/10.11591/ijeecs.v31.i3.pp1515-1522.

P. K. Narayan, S. Narayan, R. E. Rahman, dan I. Setiawan, "Bitcoin price growth and Indonesia's monetary system," Emerg. Mark. Rev., vol. 38, no. S1566014118302796, hlm. 364-376, Mar. 2019. DOI: https://doi.org/10.1016/j.ememar.2018.11.005.

A. Noor, M. A. Arifin, dan D. P. W. Astuti, "Crypto Assets and Regulation: Taxonomy and Framework Regulatory of Crypto Assets in Indonesia," J. Etika Demokrasi, vol. 8, no. 3, hlm. 303-315, Aug. 2023. DOI: https://doi.org/10.26618/jed.v%vi%i.10886.

Kaggle, "Bitcoin Historical Dataset," 2024. [Online]. Tersedia: Bitcoin Historical Dataset.

B. Shaju dan V. Narayan, "Prediction Model for Stock Trading using Combined Long Short Term Memory and Neural Prophet with Regressors," International Journal of Intelligent Engineering and Systems, vol. 16, no. 6, hlm. 956-963, 2023. DOI: https://doi.org/10.22266/ijies2023.1231.79.

Y.-T. Huang, Y.-L. Bai, Q.-H. Yu, L. Ding, dan Y.-J. Ma, "Application of a hybrid model based on the Prophet model, ICEEMDAN and multi-model optimization error correction in metal price prediction," Resour. Policy, vol. 79, no. S0301420722004123, hlm. 102969, 2022. DOI: https://doi.org/10.1016/j.resourpol.2022.102969.

M. Beniwal, A. Singh, dan N. Kumar, "Forecasting multistep daily stock prices for long-term investment decisions: A study of deep learning models on global indices," Engineering Applications of Artificial Intelligence, vol. 129, no. 107617, hlm. 107617, Mar. 2024. DOI: https://doi.org/10.1016/j.engappai.2023.107617

N. S. Wen dan L. S. Ling, "Evaluation of Cryptocurrency Price Prediction Using LSTM and CNNs Models," Int. J. Informat. Visual., vol. 7, no. 3-2, hlm. 2016-2024, 2023. DOI: https://doi.org/10.1234/jitcs.2020.602.

A. T. Haryono, R. Sarno, dan K. R. Sungkono, "Stock price forecasting in Indonesia stock exchange using deep learning: a comparative study," International Journal of Electrical and Computer Engineering, vol. 14, no. 1, hlm. 861-869, Feb. 2024. DOI: http://doi.org/10.11591/ijece.v14i1.pp861-869.

S. Pasak dan R. Jayadi, "Investment Decision on Cryptocurrency: Comparing Prediction Performance Using ARIMA and LSTM," J. Inform. Syst. Innov., vol. 5, no. 2, hlm. 407-427, June 2023. DOI: https://doi.org/10.51519/journalisi.v5i2.473.

A. Bâra dan S.-V. Oprea, "An ensemble learning method for Bitcoin price prediction based on volatility indicators and trend," Engineering Applications of Artificial Intelligence, vol. 133, no. 107991, hlm. 107991, Juli 2024. DOI: https://doi.org/10.1016/j.engappai.2024.107991

Additional Files

Published

2025-06-10

How to Cite

[1]
A. K. . Wijaya, A. F. . Gaib, I. G. N. B. F. . Mahayudha, N. . Andini, and T. F. . Zanestri, “Optimising Bitcoin Price Forecasting Using Lstm, Gru, Prophet, Var, And Es Multi-Model Approaches”, J. Tek. Inform. (JUTIF), vol. 6, no. 3, pp. 1095–1112, Jun. 2025.