Comparative Study of Hybrid ARIMA-LSTM and ARIMAX-LSTM for Bitcoin Forecasting with Data Partitioning

Fikrie Hartanta Sembiring, Regita Putri Permata, Rifdatun Ni'mah

Abstract


The extreme volatility of Bitcoin prices poses significant challenges for accurate forecasting using conventional models. While ARIMA excels at capturing linear trends, it struggles with non-linear dynamics; conversely, LSTM networks can model non-linearity but often overfit noisy data. To address these limitations, this study investigates six forecasting configurations: standalone ARIMAX, standalone LSTM, and four hybrid ARIMA/ARIMAX-LSTM models employing both single-split and two-stage split strategies. A comprehensive out-of-sample evaluation on daily Bitcoin closing prices reveals that the two-stage split hybrid ARIMA-LSTM achieves a remarkable MAPE of 2.60%, outperforming all other configurations. The results demonstrate that residual structure and strategic data partitioning critically influence hybrid model performance by enhancing residual learnability. These findings offer practical guidance for researchers and practitioners designing robust forecasting pipelines for highly volatile financial markets.

Keywords


Bitcoin forecasting; ARIMA; LSTM; Hybrid model; Time series

Full Text:

PDF

References


[1] Nikolaos Antonakakis, Ioannis Chatziantoniou, and David Gabauer. “Cryptocurrency market contagion: Market uncertainty, market complexity, and dynamic portfolios”. Journal of International Financial Markets, Institutions and Money 61 (July 2019), pp. 37–51. DOI: https://doi.org/10.1016/j.intfin.2019.02.003.

[2] Yuan Zeng and Huilin Zhu. “Short-term prediction of bitcoin value based on ARIMA model”. In: International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2022). Ed. by Steven Guan and Haibin Zhu. SPIE, Sept. 2022, p. 26. DOI: https://doi.org/10.1117/12.2648797.

[3] Shaen Corbet, Brian Lucey, Andrew Urquhart, and Larisa Yarovaya. “Cryptocurrencies as a financial asset: A systematic analysis”. International Review of Financial Analysis 62 (Mar. 2019), pp. 182–199. DOI: https://doi.org/10.1016/j.irfa.2018.09.003.

[4] Shakir Khan and Hela Alghulaiakh. “ARIMA Model for Accurate Time Series Stocks Forecasting”. International Journal of Advanced Computer Science and Applications 11.7 (2020). DOI: https://doi.org/10.14569/IJACSA.2020.0110765.

[5] Yiqing Hua. “Bitcoin price prediction using ARIMA and LSTM”. E3S Web of Conferences 218 (Dec. 2020), p. 01050. DOI: https://doi.org/10.1051/e3sconf/202021801050.

[6] Tolga Ergen and Suleyman Serdar Kozat. “Unsupervised Anomaly Detection With LSTM Neural Networks”. IEEE Transactions on Neural Networks and Learning Systems 31.8 (Aug. 2020), pp. 3127–3141. DOI: https://doi.org/10.1109/TNNLS.2019.2935975.

[7] Moch Farryz Rizkilloh and Sri Widiyanesti. “Prediksi Harga Cryptocurrency Menggunakan Algoritma Long Short Term Memory (LSTM)”. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 6.1 (Feb. 2022), pp. 25–31. DOI: https://doi.org/10.29207/resti.v6i1.3630.

[8] Emmanuel Dave, Albert Leonardo, Marethia Jeanice, and Novita Hanafiah. “Forecasting Indonesia Exports using a Hybrid Model ARIMA-LSTM”. Procedia Computer Science 179 (2021), pp. 480–487. DOI: https://doi.org/10.1016/j.procs.2021.01.031.

[9] Navmeen Latif, Joseph Durai Selvam, Manohar Kapse, Vinod Sharma, and Vaishali Mahajan. “Comparative Performance of LSTM and ARIMA for the Short-Term Prediction of Bitcoin Prices”. Australasian Accounting, Business and Finance Journal 17.1 (2023), pp. 256–276. DOI: https://doi.org/10.14453/aabfj.v17i1.15.

[10] Supriti Khanderwal and Debasis Mohanty. “Stock Price Prediction Using ARIMA Model”. International Journal of Marketing & Human Resource Research 2.2 (Apr. 2021), pp. 98–107. DOI: https://doi.org/10.47747/ijmhrr.v2i2.235.

[11] Wenxing Lu, Haidong Rui, Changyong Liang, Li Jiang, Shuping Zhao, and Keqing Li. “A Method Based on GA-CNN-LSTM for Daily Tourist Flow Prediction at Scenic Spots”. Entropy 22.3 (Feb. 2020), p. 261. DOI: https://doi.org/10.3390/e22030261.

[12] Rui Zhang, Zhen Guo, Yujie Meng, Songwang Wang, Shaoqiong Li, Ran Niu, Yu Wang, Qing Guo, and Yonghong Li. “Comparison of ARIMA and LSTM in Forecasting the Incidence of HFMD Combined and Uncombined with Exogenous Meteorological Variables in Ningbo, China”. International Journal of Environmental Research and Public Health 18.11 (June 2021), p. 6174. DOI: https://doi.org/10.3390/ijerph18116174.

[13] Linxi Pan. “Cryptocurrency Price Prediction Based on ARIMA, Random Forest and LSTM Algorithm”. BCP Business & Management 38 (Mar. 2023), pp. 3396–3404. DOI: https://doi.org/10.54691/bcpbm.v38i.4313.

[14] Nrusingha Tripathy, Sarbeswara Hota, Debahuti Mishra, Pranati Satapathy, and Subrat Kumar Nayak. “Empirical Forecasting Analysis of Bitcoin Prices”. International Journal of Electrical and Computer Engineering Systems 15.1 (Jan. 2024), pp. 21–29. DOI: https://doi.org/10.32985/ijeces.15.1.3.

[15] Djarot Hindarto. “Comparison of RNN Architectures and Non-RNN Architectures in Sentiment Analysis”. Sinkron: Jurnal dan Penelitian Teknik Informatika 7.4 (2023), pp. 2537–2546. DOI: https://doi.org/10.33395/sinkron.v8i4.13048.

[16] Soumik Ray, Achal Lama, Pradeep Mishra, Tufleuddin Biswas, Soumitra Sankar Das, and Bishal Gurung. “An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique”. Applied Soft Computing 149 (Dec. 2023), p. 110939. DOI: https://doi.org/10.1016/j.asoc.2023.110939.




DOI: https://doi.org/10.18860/cauchy.v10i2.35118

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Fikrie Hartanta Sembiring, Regita Putri Permata, Rifdatun Ni'mah

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

Editorial Office
Mathematics Department,
Maulana Malik Ibrahim State Islamic University of Malang
Gajayana Street 50 Malang, East Java, Indonesia 65144
e-mail: cauchy@uin-malang.ac.id

Creative Commons License
CAUCHY: Jurnal Matematika Murni dan Aplikasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.