Predicting bitcoin cryptocurrency price behavior based on ARIMA and NNAR modelling

Abstract

The development of models to predict the behavior of the Bitcoin cryptocurrency, using a public database (Yahoo! Finance) to predict price trends. The models used were ARIMA and NNAR with the validation of the models being carried out based on the daily closing values of the asset. Both models did not differ significantly, however the adjusted model NNAR (2.2) had a slightly better fit to the original data series, presenting an MPE (Mean Percentage Error) of -0.102.

Keywords

• ARIMA
• NNAR
• Time Series Analysis
• Bitcoin
• prediction