Implementation of Support Vector Regression for Polkadot Cryptocurrency Price Prediction

Abstract

Cryptocurrency investment is an investment instrument that has high risk but also has a greater advantage than other investment instruments. To make a big profit, investors need to analyze cryptocurrency investments to predict the price of the cryptocurrency to be purchased. The highly volatile movement of cryptocurrency prices makes it difficult for investors to predict those prices. Data mining is the process of extracting large amounts of information from data by collecting, using data, the history of data relationship patterns, and relationships in large data sets. Support Vector Regression has the advantage of doing accurate cryptocurrency price predictions and can overcome the problem of overfitting by itself. Polkadot is one of the cryptocurrencies that are often used as investment instruments in the world of cryptocurrencies. Polkadot cryptocurrency price prediction analysis using the Support Vector Regression algorithm has a good predictive accuracy value, including for Polkadot daily closing price data, namely with a radial basis function (RBF) kernel with cost parameters C = 1000 and gamma = 0.001 obtained model accuracy of 90.00% and MAPE of 5.28 while for linear kernels with parameters C = 10 obtained an accuracy of 87.68% with a MAPE value of 6.10. It can be concluded that through parameter tuning, the model formed has an accuracy value and the best MAPE is to use a radial kernel basis function (RBF) with cost parameters C = 1000 and gamma = 0.001. The results show that the Support Vector Regression method is quite good if used for the prediction of Polkadot cryptocurrencies.

Improving Cryptocurrency Price Prediction Accuracy with Multi-Kernel Support Vector Regression Approach

“…Later, training and testing datasets were split with an 80% and 20% ratio. Using a GSO technique for tuning the hyper parameters, the authors used a variety of kernel functions, including linear and RBF, for the SVR machine-learning model [16]. Thus, RBF kernels achieve a better regression result with a 5.289 MAPE and 90% R 2 score.…”

“…According to Deny Haryadi et al [16], their SVR model outperforms the risk of investing in cryptocurrencies. DOT cryptocurrency stock price is predicted using linear kernels and RBF kernels with minmax normalization.…”

“…The proposed work involved gathering historical daily cryptocurrency stock prices for Bitcoin(BTC), Ethereum(ETH), and Polkadot(DOT) [16,17,19], comprising date, open price, high price, low price, close price, adjusted close price, and volume. The datasets used for the work were gathered from Yahoo Finance.…”

Improved LSTM Method of Predicting Cryptocurrency Price Using Short-Term Data

“…Next, data splitting into separate training and testing data sets are performed for using them later to build and evaluate the machine learning model. The amount of training data usually have a larger percentage in comparison to the testing data [22]. The scenarios in this study aim to develop optimal data allocation for short-term data to predict the price of each cryptocurrency.…”

Peramalan Harga Mata Uang Kripto Solana Menggunakan Metode Support Vector Regression (Svr)

“…Salah satu cryptocurrency yang banyak diminati oleh investor atau trader yaitu Solana. Menurut situs coinmarketcap.com, Solana menduduki rangking 10 besar coin market cap dunia [4]. Solana adalah blockchain dengan kemampuan kontrak pintar yang mendukung pengembangan sistem keuangan terdesentralisasi dan berbagai aplikasi kripto, mirip dengan Ethereum [5].…”