Machine Learning Approaches to Forecast Ethereum Price Dynamics: An Evaluation Study

Abstract

Machine learning techniques have emerged as potential tools in the field of extensive research led by the growing interest in predicting the future price of Ethereum. This paper fills a major knowledge gap in the area by reviewing and analysing important literature on Ethereum price forecasting, with a focus on Ethereum and it is applicable on other cryptocurrencies as well. By using machine learning models, such as random forest and linear regression, this study fills the gap by comparing the models' ability to predict Ethereum prices properly and provides insightful information for researchers and investors. The implications of these results for the analysis of the cryptocurrency market are noteworthy, as they may reduce the risks associated with the erratic cryptocurrency market and open the door for more studies to improve prediction techniques in this ever-changing environment. The study emphasises flexibility and effectiveness in navigating complicated cryptocurrency marketplaces, which advances the understanding of machine learning applications in Ethereum price forecasting.