CRYPTOCURRENCY PRICE PREDICTION USING SUPPORT VECTOR REGRESSION
Article Sidebar
Read Counter : 31
Download : 25
Main Article Content
Abstract
The rise of cryptocurrencies in the wake of the Industrial Revolution 4.0 has changed the economic landscape, providing an innovative alternative to conventional currencies. These digital currencies based on blockchain technology offer unparalleled flexibility, transparency, speed and transaction costs. However, the volatile nature of cryptocurrency prices poses challenges, especially for novice investors. This research explores the application of Support Vector Regression (SVR) models, specifically Polynomial Kernel SVR, to predict cryptocurrency prices. Using real-time data from Yahoo Finance for popular cryptocurrencies such as Bitcoin, Ethereum, Binance Coin, Chainlink, XRP, Cardano, and Dogecoin, this study carefully evaluates various SVR scenarios. The results show that the Polynomial Kernel SVR method, with optimized parameters, achieves an average accuracy of 44.92% as measured by R2 Square and an average error of 11.3% as measured by RMSE (Root Mean Square Error).
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
[1] Anisa, D., Anggraini, T., & Tambunan, K. (2023). “Analisis Cryptocurrency Sebagai Alat Alternatif Berinvestasi Di Indonesia”. Owner, 7(3), 2674–2682. doi: 10.33395/owner.v7i3.1698.
[2] Ben Fraj, M. (2018). In Depth: Parameter tuning for SVC. Retrieved from https://medium.com/all-things-ai/in-depth-parameter-tuning-for-svc-758215394769
[3] Cheng, Q., Liu, X., & Zhu, X. (2019). “Cryptocurrency momentum effect: DFA and MF-DFA analysis”. Phys. A Stat. Mech. its Appl., 526(80), 120847. doi: 10.1016/j.physa.2019.04.083.
[4] Chicco, D., Warrens, M. J., & Jurman, G. (2021). “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation”. PeerJ Comput. Sci., 7, 1–24. doi: 10.7717/PEERJ-CS.623.
[5] Elsa. (2023). “PENERAPAN METODE SUPPORT VECTOR REGRESSION (SVR) MENGGUNAKAN KERNEL LINEAR, POLINOMIAL, DAN RADIAL DENGAN GRID SEARCH OPTIMIZATION”.no. Mi, pp. 5–24.
[6] Huda, N., & Hambali, R. (2020). “Risiko dan Tingkat Keuntungan Investasi Cryptocurrency. J. Manaj. dan Bisnis Performa”. 17(1), 72–84. doi: 10.29313/performa.v17i1.7236.
[7] Iskandar, D., Afriani, Pratiwi, & Effendi, E. (2021). “Analisis Teknik Penerjemahan pada Abstrak Jurnal IJAI”. J. Humanit. Soc. Sci., 3(1), 9–22. doi: 10.36079/lamintang.jhass-0301.187.
[8] Lopez-Martin, C., Azzeh, M., Bou-Nassif, A., & Banitaan, S. (2019). “Upsilon-SVR Polynomial Kernel for Predicting the Defect Density in New Software Projects”. Proc. - 17th IEEE Int. Conf. Mach. Learn. Appl. ICMLA 2018, pp. 1377–1382. doi: 10.1109/ICMLA.2018.00224.
[9] Panessai, I. Y., Iskandar, D., Afriani, Pratiwi, & Effendi, E. (2021). “Analisis Teknik Penerjemahan pada Abstrak Jurnal “. Humanit. Soc. Sci., 3(1), 9–22. doi: 10.36079/lamintang.jhass-0301.187.
[10] Purnama, D. I., & Setianingsih, S. (2020). “Support vector regression (SVR) model for forecasting the number of passengers on domestic flights at Sultan Hasanudin airport Makassar”. J. Mat. Stat. dan Komputasi, vol. 16, no. 3, p. 391. doi: 10.20956/jmsk.v16i3.9176.
[11] Sidik, A. P. (2020). Diagnosis of Types of Diseases in Cassava Plant by Bayes Method. J. Inform., vol. 4, no. 2, p. 69. doi: 10.15575/join.v4i2.379.
[12] Siregar, A. M., Faisal, S., Widiharto, B., Informatika, T., Perjuangan, U. B., & Ronggowaluyo, J. (2022). “Model Prediksi Penderita Covid 19 Di Indonesia Menggunakan Metode Support Vector”. Konf. Nas. Penelit. dan Pengabdi., pp. 79–90.