Bitcoin World Price Forecasting: Time Series Analysis and Machine Learning Approach

The ever-growing attention to Cryptocurrencies highlights the demand for higher academic contribution to the subject. Bitcoin is a kind of Cryptocurrencies, which plays a special role in financial transactions today; hence, price prediction is of great importance. In recent years, a vast body of research has been devoted to bitcoin pricing models, but previous research suffers from high prediction errors due to the fluctuations in the price of bitcoin make room for more research. This research will use SARIMAX, as time series analysis model, XGBOOST, as a gradient method that accelerates model learning by parallelizing decision trees and long short-term memory Neural Network Model (LSTM) to predict Bitcoin price between Late 2012 to early 2021. We considered about two months as test data, which LSTM had the best prediction accuracy, R squared of 81.39 percent for test data.

Bitcoin World Price Forecasting: Time Series Analysis and Machine Learning Approach Keywords:

Time Series Analysis , XGBOOST , LSTM , Bitcoin , Price prediction.