<![CDATA[Cryptocurrency markets are volatile and complex, presenting challenges for traditional analysis. This study utilizes a Support Vector Machine (SVM) approach to predict Ethereum’s hourly price movements using historical data, including open, high, low, close prices, and trading volume. Analyzing 34,497 hourly records, the SVM model identifies three market regimes: stable conditions, directional trends, and high-volatility events.Stable conditions dominate 72.7% of the data, marked by consistent price movements and moderate trading volumes, indicating consolidation phases. Directional trends, comprising 15.7%, reflect gradual bullish or bearish price shifts influenced by market sentiment or external factors. High-volatility events, representing 11.5%, are characterized by sharp price spikes or crashes, accompanied by increased trading activity.The Silhouette Score of 0.45 highlights the difficulty of segmenting financial data due to overlapping market states. Despite this, the SVM model effectively captures nonlinear patterns, providing valuable insights into Ethereum's price behavior. This research demonstrates the potential of machine learning in cryptocurrency analysis, enabling better market understanding, improved trading strategies, and enhanced risk management. Future work could integrate advanced features and methods to further boost prediction accuracy and model performance.]]>
Copyrights © 2023
