Cryptocurrency Price Movement Prediction Using the Hybrid SARIMAX-LSTM Method

Abstract

In the digital age, the growth of blockchain technology, underpinning cryptocurrency, has been undeniable since its debut with Bitcoin in 2009. While the cryptocurrency market offers vast profit potential, its price volatility poses a significant challenge to investors and traders. Addressing this challenge, this study proposes a prediction method that fuses SARIMAX and LSTM into a Hybrid SARIMAX-LSTM model, considering trading volume as an exogenous factor. Through evaluation metrics like MSE, RMSE, MAPE, and MAE, it was found that this hybrid model provides more accurate forecasts than singular models, showcasing its potential to counteract cryptocurrency market volatility..