<![CDATA[The purpose of this study is to compare the effectiveness of two machine learning algorithms, XGBoost and Support Vector Regression (SVR), in predicting cryptocurrency prices to address the challenges posed by market volatility. This study evaluates the performance of both algorithms through various metrics including mean absolute error (MAE), root mean squared error (RMSE), mean squared error (MSE), and mean absolute percentage error (MAPE) using transaction data of 10 cryptocurrencies. The results show that XGBoost significantly outperforms SVR, achieving consistently low MAPE values across all cryptocurrencies, demonstrating its ability to effectively capture market price movements. In contrast, SVR showed mixed performance, succeeding with certain cryptocurrencies but struggling with others, highlighting their inconsistency in predicting market trends. This study concludes that XGBoost is a more effective algorithm in predicting cryptocurrency prices and demonstrates its potential to improve financial forecasting in the cryptocurrency sector.]]>
Copyrights © 2025
