Cryptocurrency Price Prediction with Deep Neural Networks: A Comparative Analysis of Machine Learning Approaches

Abstract

In the current study, the immediate correlation coefficient and root mean square error (RMSE) are combined to create a fusion model that can accurately predict cryptocurrency prices. Multivariate linear regression, MARS, artificial neural networks (ANN), random forests, support vector machines (SVM), bootstrap aggregation, decision trees, and extreme gradient boosting with XG Boost are just a few of the deep learning and machine learning models that we use. Utilizing long short-term memory (LSTM) is a crucial element. LSTM emerges as the most accurate model for predicting cryptocurrency prices during January 1, 2023, to March 31, 2023.