Leveraging LSTM for Time-Series Analysis of Cryptocurrency Prices

Abstract

Cryptocurrency prices are highly volatile and subject to rapid fluctuations, making accurate price prediction a challenging task. In recent years, Long Short-Term Memory (LSTM), a type of Recurrent Neural Network (RNN), has emerged as a promising approach for predicting time series data, such as cryptocurrency prices. In this research paper, we apply LSTM to predict the prices of cryptocurrencies, including Bitcoin and Ethereum. We use historical price and volume data as input features and evaluate the performance of LSTM using metrics such as mean absolute error (MAE) and root mean squared error (RMSE). The results of our study show that LSTM outperforms traditional statistical methods, such as linear regression, in terms of prediction accuracy. Our findings demonstrate the potential of LSTM in predicting cryptocurrency prices and provide insights into the underlying dynamics of the cryptocurrency market.