Proposing Regression and Machine Learning Methods and Auto-Regressive Integrated Moving Average Time Series in Predicting the Price of Ripple Digital Currency

This study proposes a hybrid forecasting approach for predicting the price of Ripple's digital currency, XRP, by integrating autoregressive integrated moving average (ARIMA) time series models with machine learning (ML) techniques, including linear regression and ensemble methods. Leveraging historical price data, trading volume, market sentiment, and macroeconomic indicators, the hybrid model aims to capture both temporal dependencies and broader market dynamics for enhanced prediction accuracy. Continuous monitoring and adaptation are emphasized to address the dynamic nature of the cryptocurrency market. Accordingly, the methods of linear regression, support vector machine regression, decision tree regression, and random forest regression, as well as ARIMA, are used, which obtains the root mean squared error (RMSE) values of 0.9934, 0.9667, 0.9837, 0.9854, and 0.9178 respectively. Multiple regression is the most accurate model for predicting the value of the digital currency Ripple, whereas the ARIMA time series is the least accurate forecasting model. The novelty of the work lies in the heart of the accuracy of multiple regression in price prediction.