Enhancing Bitcoin Price Forecasting: A Comparative Analysis of Advanced Time Series Models with Hyperparameter Optimization
Abstract
This paper evaluates state-of-the-art time series forecasting to predict next-day Bitcoin prices via distinct architectures and methodologies in a real-time setting. We study six advanced models, KAN, TimesNet, NBEATS, NHITS, PatchTST and BiTCN, applied to a Jan 1, 2023, to Dec 1, 2024. We simulate real world applications via a rolling forecast strategy, in which we predict daily prices from the most recent data. The dataset consisted of daily Bitcoin closing prices and data preprocessing and integrity checks for its constituent data. Additionally, rigorous accuracy and reliability were investigated using performance metrics such as the MAE, RMSE, MAPE, and R². NBEATS and NHITS were the top performers, achieving an R² score of 0.967, explaining complex patterns in volatile cryptocurrency data. The specific importance of model architecture and further hyperparameter optimization in achieving higher forecasting accuracy is highlighted in this study. The practical implications of these findings for the advancement of time series forecasting in financial markets are leveraged here, where timely and accurate forecasts are critical.
Keywords
Full Text:
PDFReferences
J. Katina, I. Katin, and V. Komarova, ‘Cryptocurrency price forecasting: a comparative analysis of autoregressive and recurrent neural network models /’, Entrep. Sustain. Issues, vol. 11, no. 4, pp. 425–436, 2024, doi: 10.9770/jesi.2024.11.4(26).
T. Mahmud, T. Akter, R. Chakma, T. Barua, M. S. Hossain, and K. Andersson, ‘Predictive Modeling of Cryptocurrency Prices Using Machine Learning Algorithms’, in 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), Jun. 2024, pp. 1–6. doi: 10.1109/ICCCNT61001.2024.10723951.
G. Mishra, A. Sharma, K. Gulia, N. Jindal, and I. N. Tripathi, ‘Time-Series Forecasting and Anomaly Detection in Ethereum: A Deep Learning Approach’.
T. Luc Minh, R. Senkerik, and T. K. Dang, ‘Predicting Bitcoin’s Price: A Critical Review of Forecasting Models and Methods’, in Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications, T. K. Dang, J. Küng, and T. M. Chung, Eds., Singapore: Springer Nature, 2024, pp. 36–50. doi: 10.1007/978-981-96-0434-0_3.
G. Vonitsanos, A. Kanavos, F. Grivokostopoulou, and S. Sioutas, ‘Optimized Price Prediction of Cryptocurrencies using Deep Learning on High-Volume Time Series Data’, in 2024 15th International Conference on Information, Intelligence, Systems & Applications (IISA), Jul. 2024, pp. 1–8. doi: 10.1109/IISA62523.2024.10786656.
A. Farooq, M. I. Uddin, M. Adnan, A. A. Alarood, E. Alsolami, and S. Habibullah, ‘Interpretable multi-horizon time series forecasting of cryptocurrencies by leverage temporal fusion transformer’, Heliyon, vol. 10, no. 22, Nov. 2024, doi: 10.1016/j.heliyon.2024.e40142.
D. Bhowmick, D. Barik, and D. Ghosh, ‘Forecasting Bitcoin Prices Using LSTM: A Comparative Evaluation with Future Prediction’, in Innovations in Data Analytics, A. Bhattacharya, S. Dutta, P. Dutta, and D. Samanta, Eds., Singapore: Springer Nature, 2024, pp. 425–449. doi: 10.1007/978-981-97-4928-7_33.
A. D. Hassan and M. M. Ibrahim, ‘Neural Foundations of Crypto Predictions: Exploring Deep and Transformer-Based Models’, Dec. 10, 2024, Social Science Research Network, Rochester, NY: 5051299. doi: 10.2139/ssrn.5051299.
M. F. B. Hossain, L. Z. Lamia, M. M. Rahman, and M. M. Khan, ‘FinBERT-BiLSTM: A Deep Learning Model for Predicting Volatile Cryptocurrency Market Prices Using Market Sentiment Dynamics’, Nov. 02, 2024, arXiv: arXiv:2411.12748. doi: 10.48550/arXiv.2411.12748.
U. Islam et al., ‘Empowering global ethereum price prediction with EtherVoyant: a state-of-the-art time series forecasting model’, Neural Comput. Appl., Aug. 2024, doi: 10.1007/s00521-024-10169-3.
M. Waseem and S. N. Singh, ‘Advanced Predictive Modelling for Bitcoin and Ethereum Price Dynamics’, in 2024 7th International Conference on Contemporary Computing and Informatics (IC3I), Sep. 2024, pp. 118–122. doi: 10.1109/IC3I61595.2024.10828868.
Y. Nie, N. H. Nguyen, P. Sinthong, and J. Kalagnanam, ‘A Time Series is Worth 64 Words: Long-term Forecasting with Transformers’, Mar. 05, 2023, arXiv: arXiv:2211.14730. doi: 10.48550/arXiv.2211.14730.
S. M. Mostafavi and A. R. Hooman, ‘Key technical indicators for stock market prediction’, Mach. Learn. Appl., vol. 20, p. 100631, Jun. 2025, doi: 10.1016/j.mlwa.2025.100631.
Q. Shi, ‘Technical indicators and aggregate stock returns: An updated look’, J. Multinatl. Financ. Manag., vol. 77, p. 100898, Mar. 2025, doi: 10.1016/j.mulfin.2025.100898.
W. Zhao, ‘Machine Learning for Economic Forecasting: A Sentiment and Time-Series’, Feb. 06, 2025, Social Science Research Network, Rochester, NY: 5127104. doi: 10.2139/ssrn.5127104.
J. Lee, M. Jeon, M. Kang, and K. Park, ‘Feature-aligned N-BEATS with Sinkhorn divergence’, Feb. 25, 2024, arXiv: arXiv:2305.15196. doi: 10.48550/arXiv.2305.15196.
S. Huang, Z. Zhao, C. Li, and L. Bai, ‘TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting’, Feb. 26, 2025, arXiv: arXiv:2502.06910. doi: 10.48550/arXiv.2502.06910.
S. Lee, J.-K. Kim, J. Kim, T. Kim, and J. Lee, ‘HiPPO-KAN: Efficient KAN Model for Time Series Analysis’, Oct. 19, 2024, arXiv: arXiv:2410.14939. doi: 10.48550/arXiv.2410.14939.
H. G. Souto, ‘Charting new avenues in financial forecasting with TimesNet: The impact of intraperiod and interperiod variations on realized volatility prediction’, Expert Syst. Appl., vol. 255, p. 124851, Dec. 2024, doi: 10.1016/j.eswa.2024.124851.
K. Xu, L. Chen, and S. Wang, ‘Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretability’, Jun. 04, 2024, arXiv: arXiv:2406.02496. doi: 10.48550/arXiv.2406.02496.
C. Challu, K. G. Olivares, B. N. Oreshkin, F. Garza, M. Mergenthaler-Canseco, and A. Dubrawski, ‘N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting’, Nov. 29, 2022, arXiv: arXiv:2201.12886. doi: 10.48550/arXiv.2201.12886.
B. N. Oreshkin, D. Carpov, N. Chapados, and Y. Bengio, ‘N-BEATS: Neural basis expansion analysis for interpretable time series forecasting’, Feb. 20, 2020, arXiv: arXiv:1905.10437. doi: 10.48550/arXiv.1905.10437.
H. Wu, T. Hu, Y. Liu, H. Zhou, J. Wang, and M. Long, ‘TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis’, Apr. 12, 2023, arXiv: arXiv:2210.02186. doi: 10.48550/arXiv.2210.02186.
O. Sprangers, S. Schelter, and M. de Rijke, ‘Parameter-efficient deep probabilistic forecasting’, Int. J. Forecast., vol. 39, no. 1, pp. 332–345, Jan. 2023, doi: 10.1016/j.ijforecast.2021.11.011.
K. G. Olivares, C. Challú, F. Garza, M. M. Canseco, and A. Dubrawski, ‘NeuralForecast: User friendly state-of-the-art neural forecasting models.’ 2022. [Online]. Available: https://github.com/Nixtla/neuralforecast
S. Watanabe, ‘Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance’, May 26, 2023, arXiv: arXiv:2304.11127. Accessed: May 12, 2024. [Online]. Available: http://arxiv.org/abs/2304.11127
T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, ‘Optuna: A Next-generation Hyperparameter Optimization Framework’, Jul. 25, 2019, arXiv: arXiv:1907.10902. doi: 10.48550/arXiv.1907.10902.
DOI: http://doi.org/10.11591/ijict.v15i2.pp535-544
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Institute of Advanced Engineering and Science
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
The International Journal of Informatics and Communication Technology (IJ-ICT)
p-ISSN 2252-8776, e-ISSN 2722-2616
This journal is published by the Intelektual Pustaka Media Utama (IPMU).