<![CDATA[Cryptocurrencies have rapidly emerged as one of the most exciting financial technology innovations in recent years. Among the various digital assets, XRP (Ripple) is one of the most popular, experiencing significant price fluctuations. This study aims to apply the Support Vector Machine (SVM) method in predicting the price of the XRP cryptocurrency, in the hope of providing a clearer picture of the investment prospects. The data used in this study includes the daily price movements of XRP from 2019 to 2023. In the research process, the date variable is selected as the input feature, and the closing price as the output to be predicted. Various kernel functions in SVM, including RBF, Polynomial, and Sigmoid, were tested to determine which one gave the best results. The results showed that the Polynomial kernel produced a Mean Absolute Percentage Error (MAPE) value of 45.40%, indicating better accuracy compared to other kernels. This study also explains the importance of choosing the right kernel function and overcoming the problem of underfitting that may occur due to the high volatility characteristics of cryptocurrencies. These findings not only enrich the understanding of machine learning techniques but also provide new insights for investors in data-based decision making. Recommendations for future research include the use of alternative prediction models and the integration of external information that can affect prices.]]>
Copyrights © 2025
