Comparative Bitcoin Price Prediction Using Multiple Machine Learning Techniques

Abstract

The cryptocurrency market is known for its inherent volatility, making accurate predictions a challenging endeavor.In this research study, investigate the efficacy of logistic regression, support vector machines (SVM), decision trees and random forests for the task of Bitcoin price prediction.To address this, conduct a thorough analysis and comparison of these machine learning models using historical Bitcoin price data.By rigorously assessing their performance and predictive capabilities, this study aims to provide valuable insights for both cryptocurrency traders and researchers operating in the dynamic digital asset landscape.These results illuminate the strengths and weaknesses of each model, shedding light on their respective abilities to forecast Bitcoin price movements.Through this research, contribute to the growing body of knowledge surrounding cryptocurrency market analysis and prediction techniques.This analysis can inform traders' decision-making processes and assist researchers in developing more robust models in the exciting and rapidly evolving realm of cryptocurrency investment and analysis.