NVIDIA Graphics Card Price Prediction Based On The Effect Of Cryptocurrency Price Using Support Vector Regression
Abstract
The growing popularity of cryptocurrencies has caused the market demand for graphics cards to reach unusual heights for their efficient cryptomining capabilities. Graphics cards are not only used for crypto mining but also video editing, video streaming, and video games, this causes an unavailability of graphics card supply due to high demand, especially for cryptomining needs and leads to unusual prices increases which makes it difficult for graphics card consumers and miners to buy graphics cards at normal price. Therefore, it is necessary to predict the price of NVIDIA graphics cards based on the influence of cryptocurrency prices. The methodology used is KDD, and the algorithm used to make predictions is SVR because its ability to overcome the overfitting problem so it can produce more accurate predictions, besides that in this study the grid search algorithm is applied to determine optimal parameters. In this study, 6 graphics cards and 2 cryptocurrencies were used which produced the 6 best prediction models which were chosen based on the RMSE value. GTX 1050 has RMSE value of 0.2028, GTX 1050 Ti has RMSE value of 0.14564, GTX 1060 has an RMSE value of 0.07629, while in the RTX 30 series, RTX 3070 has an RMSE value of 0.03178, RTX 3080 has RMSE value of 0.0388, and RTX 3090 has RMSE of 0.06259. From these results, it can be stated that RTX 30 series has better accuracy than GTX 10 series in making predictions. RBF is better than linear which only excels on the GTX 1060.
References
Awad, M., & Khanna, R. (2015). Support Vector Regression. In Efficient Learning Machines. https://doi.org/10.1007/978-1-4302-5990-9_4
Bhiantara, I. B. P. (2018). Teknologi Blockchain Cryptocurrency Di Era Revolusi Digital. Prosiding Seminar Nasional Pendidikan Teknik Informatika.
Hrsuka, J. (2021, June 16). Cryptocurrency Miners Bought 700,000 GPUs in Q1 2021. Extreme Tech. Retrieved from https://www.extremetech.com/extreme/323781-cryptocurrency-miners-bought-700000-gpus-in-q1-2021
Hsu, A., & Roger, S. (2018). How Adoption of Cryptocurrencies (e.g., Bitcoin) as a Mainstream Form of Payment Might Be Affected as High-Frequency Trading Becomes More Prevalent Among Major Currencies. Retrieved from https://aar.pausd.org/projects-2018/how-adoption-cryptocurrencies-eg-bitcoin-mainstream-form-payment-might-be-affected
Jinn, Z., Guo, K., Sun, Y., Lai, L., & Liao, Z. (2020). The Industrial Asymmetry of the Stock Price Prediction with Investor Sentiment: based on the comparison of predictive effects with SVR. Journal of Forecasting, 39(7), 1168–1178.
Leksono, S. A. A., Prastyawan, Z. G., & Veritawati, I. (2019). Prediksi Harga Kartu Grafis Yang Dipengaruhi oleh Nilai Bitcoin. JURNAL ILMIAH INFO, 11(1).
Peddie, J. (2021, June 15). Crypto-mining’s half a billion dollar impact on AIB sales. JPR (Jon Peddie Research). Retrieved from https://www.jonpeddie.com/blog/crypto-minings-half-a-billion-dollar-impact-on-aib-sales/
Putra, A. L., & Kurniawati, A. (2021). Analisis Prediksi Harga Saham PT. Astra International Tbk Menggunakan Metode Autoregressive Integrated Moving Average (ARIMA) dan Support Vector Regression (SVR). Jurnal Ilmiah KOMPUTASI, 20(3).
Putriwijaya, N. N., & Mahmudy, W. F. (2018). Peramalan Jumlah Pemakaian Air di PT. Pembangkitan Jawa Bali Unit Pembangkit Gresik Menggunakan Support Vector Regression. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 2(10), 3788–3795.
Ridwan, D. I., Setianingsih, C., & Murti, M. A. (2021). PREDIKSI PENGGUNAAN ENERGI LISTRIK DENGAN MENGGUNAKAN METODE SUPPORT VECTOR REGRESSION. EProceedings of Engineering, 8(6).
Yasin, H., Prahutama, A., & Utami, T. W. (2014). PREDIKSI HARGA SAHAM MENGGUNAKAN SUPPORT VECTOR REGRESSION DENGAN ALGORITMA GRID SEARCH. Media Statistika, 7(1).
