In this article we investigate the task of forecasting cryptocurrency prices based on time series using different modeling approaches. Several methods have been implemented and compared: the Dobeschi wavelet decomposition method for preliminary smoothing of data, a Random Forest machine learning model, a fuzzy logic system with automatic rule selection using a genetic algorithm, and a basic neural network. Each of the approaches was tested on the same time series, and their effectiveness was evaluated using the relevant accuracy metrics. We pay particular attention to how wavelet-based preprocessing (e.g., wavelet smoothing) impacts forecasting accuracy. The obtained results allow to draw conclusions about the strengths and
weaknesses of each method in the context of cryptocurrency price forecasting, as well as the feasibility of their use depending on the characteristics of the data and the task.

[1] Matviychuk A. Fuzzy logic approach to identification and forecasting of financial time series using Elliott wave theory // Fuzzy Economic Review. — 2006. — Vol. 11, no. 02. — P. 45—54. — URL:https://doi.org/10.25102/fer.2006.02.04](https://doi.org/10.25102/fer.2006.02.04).
[2] Bielinskyi A., Ivanov B., Petrenko C. Fuzzy time series forecasting using semantic artificial intelligence tools // Neuro-Fuzzy Modeling Techniques in Economics. — 2022. — No. 11. — P. 157—198. — URL:[https://doi.org/10.33111/nfmte.2022.157](https://doi.org/10.33111/nfmte.2022.157).
[3] Rhif M., Hleli H., Smara Y. Wavelet transform application for non-stationary time-series analysis: A Review // Applied Sciences. — 2019. — Vol. 9, no. 7. — P. 1345. — URL: [https://doi.org/10.3390/app9071345](https://doi.org/10.3390/app9071345).
[4] Surmann H., Selenschtschikow A. Automatic generation of fuzzy logic rule bases: Examples I // Proceedings of the First International ICSC Conference on Neuro-Fuzzy Technologies (16-19 January 2002). — Vienna, 2002. — P. 75-81.
[5] Glybovets M., Gulaeva N. Evolutionary algorithms. — Kyiv: NaUKMA, 2013. — 828 p.
[6] Matviychuk A. V. Artificial Intelligence in Economics: Neural Networks, Fuzzy Logic: Monograph. — Kyiv: KNEU, 2011. — 439 p.
[7] Matviychuk A. V. Research on the dependence of the quality of forecasting security prices by neural networks on the form of input data presentation // Collection of scientific papers of Cherkasy State Technological University. Series: Economic Sciences. — 2003. — Issue 8. — P. 147—156.
[8] Tayib H., Abdulazeez M. A. A Review of Bitcoin Price Prediction Based on Deep Learning Algorithms // The Indonesian Journal of Computer Science. — 2024. — Vol. 13, no. 2. — P. 45-58. — URL: [https://doi.org/10.33022/ijcs.v13i2.3858](https://doi.org/10.33022/ijcs.v13i2.3858).
[9] Top 10 Cryptocurrencies Historical Dataset [Електронний ресурс] // Kaggle. — URL: [https://www.kaggle.com/datasets/kaushiksuresh147/top-10-cryptocurrencies-historicaldataset](https://www.kaggle.com/datasets/kaushiksuresh147/top-10-cryptocurrencies-historicaldataset).
[10] Zhang X., Huang Z., Wu Y., Lu X., Qi E., Chen Y., Xue Z., Wang Q., Wang P., Wang W. Multi-period Learning for Financial Time Series Forecasting // Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD —25). — New York; ACM, 2025. — P. 2848—2859. —
URL: [https://doi.org/10.1145/3690624.3709422](https://doi.org/10.1145/3690624.3709422).
[11] Badar W., Ramzan S., Raza A., Fitriyani N. L., Syafrudin M., Lee S. W. Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model // Mathematics. — 2025. — Vol. 13, no. 12. — Art. 1908. — URL:
[https://doi.org/10.3390/math13121908](https://doi.org/10.3390/math13121908).
[12] Zeng Z., Kaur R., Siddagangappa S., Rahimi S., Balch T., Veloso M. Financial Time Series Forecasting using CNN and Transformer // arXiv preprint arXiv:2304.04912. — 2023. — URL:
[https://arxiv.org/abs/2304.04912](https://arxiv.org/abs/2304.04912)).
[13] Kong X., Chen Z., Liu W. et al. Deep learning for time series forecasting: a survey // Int. J. Mach. Learn. & Cybern. — 2025. — URL: [https://doi.org/10.1007/s13042-025-02560-w](https://doi.org/10.1007/s13042-025-02560-w).

[14] Kilic D. K., Ugur O. Hybrid wavelet-neural network models for time series
// Applied Soft Computing. — 2023. — Vol. 144. — Art. 110469. — URL:
[https://doi.org/10.1016/j.asoc.2023.110469](https://doi.org/10.1016/j.asoc.2023.110469) .
[15] Li Y., Dai W. Bitcoin price forecasting method based on CNN-LSTM hybrid neural network model // The Journal of Engineering. — 2020. — P. 344—347. — URL: [https://doi.org/10.1049/joe.2019.1203](https://doi.org/10.1049/joe.2019.1203).
[16] Wu J., Zhang X., Huang F., Zhou H., Chandra R. Review of deep learning models for crypto price prediction: Implementation and evaluation // arXiv preprint arXiv:2405.11431. — 2024. — URL:
[https://arxiv.org/abs/2405.11431](https://arxiv.org/abs/2405.11431).
[17] Ahmed B., Abedin M. Z., Hajek P., Yuan K. Cryptocurrency price forecasting — A comparative analysis of ensemble learning and deep learning methods // International Review of Financial Analysis. — 2024. — Vol. 92. — Art. 103055. — URL: [https://doi.org/10.1016/j.irfa.2023.103055](https://doi.org/10.1016/j.irfa.2023.103055).