Forecasting Twitter's Favorite Cryptocurrencies Based on a Comparative Assessment of SARIMA, LSTM and Fb Prophet Machine Learning Approach

Abstract

The complicated combination of long-term patterns, short-term seasonality, and uncertainty has made selecting an appropriate forecasting model for cryptocurrency prices challenging. To forecast the future prices of the cryptocurrencies, this study compared three machine learning models: the Seasonal Auto-Regressive Integrated Moving Average (SARIMA), the Long Short-Term Memory (LSTM), and the Facebook (Fb) Prophet for the period of 2017 till 2023. It was discovered that the FbProphet model works well in predicting the daily price forecasts of Bitcoin and Dogecoin with low mean squared error (MSE), using time series datasets from 2017 through 2023 as the training data to anticipate 12 months of unseen data. While predicting the future from 2023 to 2024, Fb Prophet stated that Dogecoin is most likely to remain stable while Bitcoin price is most likely to continue falling. The LSTM model performs better than the other models based on forecasting results.