PERAMALAN HARGA MATA UANG KRIPTO SOLANA MENGGUNAKAN METODE SUPPORT VECTOR REGRESSION (SVR)
-
Dewi Marini Umi Atmaja(1*)
Universitas Medika Suherman
-
Arif Rahman Hakim(2)
Universitas Medika Suherman
(*) Corresponding Author
Abstract
Cryptocurrencies have great potential to be adopted in Indonesia as an alternative to investing. One of the cryptocurrencies that investors or traders are interested in is Solana. Fluctuating price. movements make cryptocurrency investments considered. speculative so the risks. faced are very high. With this, we need a system or model that can help investors or traders to predict prices so that investors or traders have material for consideration in making decisions. The results of the descriptive analysis can be seen that in the period from April 10, 2020 to May 30, 2022, Solana's daily closing price movement fluctuates. The Support Vector Regression model obtained for Solana's daily closing price data, namely the Linear kernel with cost parameter C = 1000, obtained an. accuracy of 97.44% and MAPE 9.93 while for the Radial Basis Function. (RBF) kernel with cost parameter C = 1000 an .gamma = 0.1 obtained an accuracy of 87.76% with a MAPE value of 8.14. It can be concluded that through parameter tuning, the model formed has an accuracy value and the. best MAPE is to use a linear kernel with a cost parameter of C = 1000.
Downloads
References
I. T. Julianto, D. Kurniadi, M. R. Nashrul-loh, and A. Mulyani, "Compa-rison of Data Mining Algorithm For Forecasting Bitccoin Crypto Currency Trends," J. Tek. Inform., vol. 3, no. 2, pp. 245-248,2022, doi:10.20884/1.jutif. 2022. 3.2.194.
Moch Farryz Rizkilloh and Sri Widiya-nesti, "Prediksi Harga Cryptocurrency Menggunakan Algoritma Long Short Term Memory (LSTM)," J. RESTI (Reka-yasa Sist. dan Teknol. Informasi), vol. 6, no. 1, pp. 25-31, 2022, doi: 10. 29207/ resti.v6i1.3630.
https://doi.org/10.29207/resti.v6i1.3630
U. P. Wibowo, Jondri, and A. Aditsania, "Prediksi Mata Uang Digital (bitcoin) Menggunakan Feed Forward Neural Network," e-Proceeding Eng. Vol.6, No.1 April 2019 , vol. 6, no. 1, pp. 2539-2544, 2019, [Online]. Available: https://open librarypublications.telkomuniversity.ac.id/index.php/engineering/article/view/8720/8586
D. Haryadi, A. Rahman, D. Marini, U. Atmaja, and S. Nurgaida, "Implementa-tion of Support Vector Regression for Polkadot Cryptocurrency Price Predic-tion," vol. 6, no. May, pp. 201-207, 2022.
https://doi.org/10.30630/joiv.6.1-2.945
Nilda Aulia, "Prediksi Harga Ethereum Berdasarkan Informasi Blockchain Meng-gunakan Metode Long Short Term Me-mory," J. Chem. Inf. Model., vol. 53, no. 9, pp. 1689-1699, 2013.
G. B. Blocks, "An Introduction to Sola-na," no. December, 2021.
R. A. Wibowo and B. Rikumahu, "Perama lan Dengan Volatilitas Frekuensi Tinggi Untuk Vector Regression Dan Regresi Linier Forecasting High Frequency Volatility for Cryptocurrencies and Con ventional Currencies With Support Vector Regression ( a Study on October 2017 - September 2018 Perio," vol. 6, no. 3, pp. 5647-5652, 2019.
D. I. Purnama and S. Setianingsih, "Sup-port vector regression (SVR) model for forecasting number of passengers on domestic flights at Sultan Hasanudin airport Makassar," J. Mat. Stat. dan Kom-putasi, vol. 16, no. 3, p. 391, 2020, doi: 10.20956/jmsk.v16i3.9176.
https://doi.org/10.20956/jmsk.v16i3.9176
N. P. N. Hendayanti, I. K. P. Suniantara, and M. Nurhidayati, "Penerapan Support Vector Regression (Svr) Dalam Mempre-diksi Jumlah Kunjungan Wisatawan Domestik Ke Bali," J. Varian, vol. 3, no. 1, pp. 43-50, 2019, doi: 10.30812/vari-an.v3i1.506.
https://doi.org/10.30812/varian.v3i1.506
H. C. S. Ningrum, "Perbandingan Metode Support Vector Machine (SVM) Linear, Radial Basis Function (RBF), dan Polinomial Kernel dalam Klasifikasi Bidang Studi Lanjut Pilihan Alumni UII," Tugas Akhir Stat. Univ. Islam Indones., pp. 1-90, 2018.
R. J. D. Simamora, Tibyani, and Sutrisno, "Peramalan Curah Hujan Menggunakan Metode Extreme Learning Machine," J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 10, pp. 9670-9676, 2019.
A. Nurdiansyah, M. T. Furqon, and B. Rahayudi, "Prediksi Harga Bitcoin Meng-gunakan Metode Extreme Learning Machine (ELM) dengan Optimasi Arti-ficial Bee Colony (ABC)," J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 6, pp. 5531-5539, 2019, [Online]. Available:http://j-ptiik.ub.ac.id/index.php/ j-ptiik/article/view/5507
A. R. Hakim, D. Marini, U. Atmaja, D. Haryadi, and N. Suwaryo, "Twitter Senti-ment Analysis Terhadap Pengguna E-Commerce Menggunakan Text Mining," SNTEM Semin. Nas. Teknol. Energi dan Miner., vol. 1, no. November, pp. 1227-1237, 2021.
T. M. Tamtelahitu, "Komparasi Algoritma Clustering dengan Dataset Penyebaran Covid-19 di Indonesia Periode Maret-Mei 2020," J. Teknol. Technoscientia, vol. 13, no. 1, pp. 27-34, 2020.
C. No, "Government to Person ( G2P ) Terhadap Penyaluran Bantuan Sosial di Indonesia Teknologi Blockchain dan Po-tensinya Pentingnya Reformasi Data Bagi Reformasi Perlindungan Sosial," vol. VI, 2021.
R. E. Caraka, H. Yasin, and A. W. Basyi-ruddin,"Peramalan Crude Palm Oil (CPO) Menggunakan Support Vector Regression Kernel Radial Basis," J. Mat., vol. 7, no. 1, p. 43, 2017, doi: 10.24843/jmat.2017. v07.i01.p81.
This work is licensed under CC BY-SA 4.0
