A Hybrid Ensemble Stacking Framework Integrating Long Short-Term Memory and Random Forest for Bitcoin Price Forecasting

Authors

  • Akhlis Munazilin Diponegoro University; Universitas Ibrahimy, Indonesia
  • Mochamad Agung Wibowo Diponegoro University, Indonesia
  • Rizky Parlika Diponegoro University, Indonesia
Pages Icon

DOI:

https://doi.org/10.63158/journalisi.v8i2.1537

Keywords:

Bitcoin, Hybrid Ensemble Stacking, Long Short-Term Memory, Time-series Forecasting, Cryptocurrency Forecasting

Abstract

Bitcoin is a non-linear and non-stationary digital asset that has become a highly volatile asset challenging the usual prediction models. In this paper, the authors present a problem-specific Hybrid Ensemble Stacking approach, the proposed approach, which combines the benefits of Long Short-Term Memory (LSTM) in terms of capturing long-term temporal variations with the power of Random Forest (RF) to process complex technical characteristics. The model follows a two-tier structure with a split ratio of 90:10 using BTC/USD historical data of Yahoo Finance and Binance (20102025) to combine the predictions of base learners with the use of a Linear Regression meta-learner. Findings show that pure LSTM has a low RMSE and MAE, but the Hybrid model has the best Mean Absolute Percentage Error (MAPE) of 3.54%. This means that the stacking mechanism will provide a more balanced error percentage, that is, it will enhance stability in forecasting at the phases of price discovery. It is novel in the sense that it uses macro-technical indicators to stabilize predictions in the face of market anomalies as a stacking scheme. These results have real-life implications on developers of financial systems in creating consistent crypto-asset risk management instruments.

Downloads

Download data is not yet available.

References

[1] J. Chen, “Analysis of Bitcoin Price Prediction Using Machine Learning,” J. Risk Financ. Manag., vol. 16, no. 1, 2023, doi: 10.3390/jrfm16010051.

[2] A. Munazilin, M. A. Wibowo, and R. Parlika, “Bitcoin Price Prediction : A Systematic Literature Review and Bibliometric Analysis,” 2025 9th Int. Conf. Inf. Technol. Inf. Syst. Electr. Eng., pp. 277–282, 2025, doi: 10.1109/ICITISEE68184.2025.11355086.

[3] A. Akgul, E. E. Şahin, and F. Y. Şenol, “Blockchain-based Cryptocurrency Price Prediction with Chaos Theory, Onchain Analysis, Sentiment Analysis and Fundamental-Technical Analysis,” Chaos Theory Appl., vol. 4, no. 3, pp. 157–168, 2022, doi: 10.51537/chaos.1199241.

[4] N. Latif, J. D. J. D. Selvam, M. Kapse, V. Sharma, and V. C. Mahajan, “Comparative Performance of LSTM and ARIMA for the Short-Term Prediction of Bitcoin Prices,” Australas. Accounting, Bus. Financ. J., vol. 17, no. 1, pp. 256–276, 2023, doi: 10.14453/aabfj.v17i1.15.

[5] O. Omole and D. L. Enke, “Deep learning for Bitcoin price direction prediction: models and trading strategies empirically compared,” Financ. Innov., vol. 10, no. 1, 2024, doi: 10.1186/s40854-024-00643-1.

[6] W. Badar, S. Ramzan, A. Raza, N. L. Fitriyani, M. Syafrudin, and S. W. Lee, “Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model,” Mathematics, vol. 13, no. 12, 2025, doi: 10.3390/math13121908.

[7] F. Orte, J. Mira, M. J. Sánchez, and P. Solana, “A random forest-based model for crypto asset forecasts in futures markets with out-of-sample prediction,” Res. Int. Bus. Financ., vol. 64, no. November 2022, 2023, doi: 10.1016/j.ribaf.2022.101829.

[8] M. Aswadi and U. Ependi, “Predicting Bitcoin and Ethereum Prices Using the Long Short- Term Memory ( LSTM ) Model,” J. Inf. Syst. Informatics, vol. 7, no. 3, pp. 3046–3061, 2025, doi: 10.51519/journalisi.v7i3.1228.

[9] N. Tripathy, S. Hota, D. Mishra, S. K. Nayak, S. S. Dalai, and J. Tripathy, “Cryptocurrency Price Prediction: A Comprehensive Analysis of High-dimensional Features with Deep Learning Techniques,” in 2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/IC-SIT63503.2024.10862895.

[10] N. Tripathy, P. Satapathy, S. Hota, S. K. Nayak, and D. Mishra, “Empirical Forecasting Analysis of Bitcoin Prices: A Comparison of Machine Learning, Deep Learning, and Ensemble Learning Models,” Int. J. Electr. Comput. Eng. Syst., vol. 15, no. 1, pp. 21 – 29, 2024, doi: 10.32985/ijeces.15.1.3.

[11] M. Frohmann, M. Karner, S. Khudoyan, R. Wagner, and M. Schedl, “Predicting the Price of Bitcoin Using Sentiment-Enriched Time Series Forecasting,” Big Data Cogn. Comput., vol. 7, no. 3, 2023, doi: 10.3390/bdcc7030137.

[12] Y. Zhu et al., “Price Prediction of Bitcoin Based on Adaptive Feature Selection and Model Optimization,” Mathematics, vol. 11, no. 6, 2023, doi: 10.3390/math11061335.

[13] P. L. Seabe, C. R. B. Moutsinga, and E. Pindza, “Sentiment-driven cryptocurrency forecasting: analyzing LSTM, GRU, Bi-LSTM, and temporal attention model (TAM),” Soc. Netw. Anal. Min., vol. 15, no. 1, pp. 1–27, 2025, doi: 10.1007/s13278-025-01463-6.

[14] P. L. Seabe, C. R. Bambe Moutsinga, E. Pindza, C. R. B. Moutsinga, and E. Pindza, “Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach,” Fractal Fract., vol. 7, no. 2, 2023, doi: 10.3390/fractalfract7020203.

[15] N. Tripathy, S. K. Nayak, and S. Prusty, “A comparative analysis of Silverkite and inter-dependent deep learning models for bitcoin price prediction,” Front. Blockchain, vol. 7, 2024, doi: 10.3389/fbloc.2024.1346410.

[16] R. Bourday, I. Aatouchi, M. A. Kerroum, and A. Zaaouat, “Cryptocurrency Forecasting Using Deep Learning Models: A Comparative Analysis,” HighTech Innov. J., vol. 5, no. 4, pp. 1055–1067, 2024, doi: 10.28991/HIJ-2024-05-04-013.

[17] A. Ladhari and H. Boubaker, “Deep Learning Models for Bitcoin Prediction Using Hybrid Approaches with Gradient-Specific Optimization,” Forecasting, vol. 6, no. 2, pp. 279 – 295, 2024, doi: 10.3390/forecast6020016.

[18] P. L. Seabe, E. Pindza, C. R. B. Moutsinga, M. Aphane, C. R. Bambe Moutsinga, and M. M Aphane, “Temporal Attention-Enhanced Stacking Networks: Revolutionizing Multi-Step Bitcoin Forecasting,” Forecasting, vol. 7, no. 1, 2025, doi: 10.3390/forecast7010002.

[19] M. R. Kabir, D. Bhadra, M. Ridoy, and M. G. Milanova, “LSTM–Transformer-Based Robust Hybrid Deep Learning Model for Financial Time Series Forecasting,” Sci, vol. 7, no. 1, 2025, doi: 10.3390/sci7010007.

[20] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.

[21] K. Murray, A. Rossi, D. Carraro, and A. Visentin, “On Forecasting Cryptocurrency Prices: A Comparison of Machine Learning, Deep Learning, and Ensembles,” Forecasting, vol. 5, no. 1, pp. 196–209, 2023, doi: 10.3390/forecast5010010.

[22] Z. Ye, Y. Wu, H. Chen, Y. Y. Pan, and Q. Jiang, “A Stacking Ensemble Deep Learning Model for Bitcoin Price Prediction Using Twitter Comments on Bitcoin,” Mathematics, vol. 10, no. 8, 2022, doi: 10.3390/math10081307.

[23] M. Z. Maliha, A. S. Trisha, A. M. T. Khan, P. Das, M. I. Hossain, and R. Rahman, “A Deep Learning Approach to Predict Cryptocurrency Price by Evaluating Sentiment and Stock Market Correlations,” Lect. Notes Networks Syst., vol. 867 LNNS, pp. 3 – 17, 2024, doi: 10.1007/978-981-99-8937-9_1.

[24] E. Koosha, M. Seighaly, and E. Abbasi, “Measuring the Accuracy and Precision of Random Forest, Long Short-Term Memory, and Recurrent Neural Network Models in Predicting the Top and Bottom of Bitcoin price,” J. Math. Model. Financ., vol. 2, no. 2, pp. 107 – 128, 2022, doi: 10.22054/jmmf.2023.15183.

[25] M. Bagheri and P. S. Giudici, “Accurate, Secure and Explainable bitcoin forecasting,” Phys. A Stat. Mech. its Appl., vol. 678, 2025, doi: 10.1016/j.physa.2025.130974.

[26] R. Bourday, I. Aattouchi, and M. Ait Kerroum, “A Transfer Learning–Enhanced Hybrid Deep Learning Framework for Bitcoin Price Forecasting Using Market Sentiment and Time Series Data,” Int. J. Inf. Eng. Electron. Bus., vol. 17, no. 5, pp. 1–17, 2025, doi: 10.5815/ijieeb.2025.05.01.

[27] Y. Wang, M. F. Ghazali, R. Ab Razak, and M. A. S. Zaidi, “Complex system and PS-LSTM prediction of cryptocurrencies, stocks, bonds, exchange rates and commodities,” Phys. A Stat. Mech. its Appl., vol. 679, 2025, doi: 10.1016/j.physa.2025.130976.

[28] 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.

[29] M. Zatwarnicki and K. Zatwarnicki, “Timing Usage of Technical Analysis in the Cryptocurrency Market,” Appl. Sci., vol. 15, no. 23, pp. 1–30, 2025, doi: 10.3390/app152312802.

[30] P. D. Quang, N. H. Duy, P. Q. Khoai, and B. D. Duong, “Integrating Moving Average Indicators with Long Short-Term Memory Model in Bitcoin Price Forecasting,” J. Appl. Data Sci., vol. 6, no. 3, pp. 1850–1864, 2025, doi: 10.47738/jads.v6i3.766.

[31] N. Kose, Y. E. Gur, and E. Ünal, “Deep Learning and Machine Learning Insights Into the Global Economic Drivers of the Bitcoin Price,” J. Forecast., vol. 44, no. 5, pp. 1666–1698, 2025, doi: 10.1002/for.3258.

[32] K. Zhen, D. Xie, and X. Hu, “A multi-feature selection fused with investor sentiment for stock price prediction,” Expert Syst. Appl., vol. 278, p. 127381, 2025, doi: 10.1016/j.eswa.2025.127381.

Downloads

Published

2026-04-12

Issue

Vol. 8 No. 2 (2026): April

Section

Articles

License

Copyright (c) 2026 Journal of Information Systems and Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors Declaration

  1. The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
  2. The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
  3. The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
  4. The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
  5. The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
  6. The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
  7. If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
  8. The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights

How to Cite

[1]
A. Munazilin, M. A. Wibowo, and R. Parlika, “A Hybrid Ensemble Stacking Framework Integrating Long Short-Term Memory and Random Forest for Bitcoin Price Forecasting”, journalisi, vol. 8, no. 2, pp. 1891–1912, Apr. 2026, doi: 10.63158/journalisi.v8i2.1537.

Most read articles by the same author(s)