The cryptocurrency market has experienced considerable fluctuations and downturns, resulting in a heightened interest in understanding the factors that influence price changes and the need for more advanced tools to manage risk and optimize trading strategies. This article introduces a machine learning-based model that leverages multiple datasets associated with various stocks and employs a range of ML techniques, including linear regression and XGBoost, to predict stock prices. The model's performance was evaluated using the Root Mean Square Error (RMSE) metric, and the results demonstrated that it outperformed traditional models in predicting cryptocurrency prices.
For two major cryptocurrencies, Bitcoin and Ethereum, linear regression (LR) models achieved the lowest RMSE values of 0.02, showcasing their effectiveness in predicting price fluctuations. Similarly, for the popular cryptocurrency Dogecoin, LR models yielded an RMSE of 0.03, signifying satisfactory prediction accuracy. These findings underline the potential of machine learning techniques in improving the accuracy of cryptocurrency price predictions.
Future research can concentrate on investigating additional ML techniques and incorporating more diverse datasets to further enhance the performance of cryptocurrency price prediction models. By expanding the scope of techniques and data sources, researchers can work towards creating even more accurate and reliable models, which can ultimately benefit investors and traders in the dynamic and volatile cryptocurrency market. This study serves as a foundation for further exploration in this field, and highlights the significance of machine learning in predicting cryptocurrency price movements.
Anahtar Kelimeler: Blockchain, Cryptocurrency, Machine Learning
|
