TY  - JOUR
T1  - Predicting Bitcoin Cryptocurrency Price Behavior based on ARIMA and NNAR modelling
A1  - Lima, Patrícia Virgínia de Santana
A1  - Cruz, David Venâncio da
A1  - Sanz, Albaro Ramon Paiva
Y1  - 2024///
KW  - prediction
KW  - Time Series Analysis
KW  - Bitcoin
KW  - forecast. ARIMA
KW  - NNAR
JF  - Socioeconomic Analytics
VL  - 2
IS  - 1
SP  - 121
EP  - 129
DO  - https://doi.org/10.51359/2965-4661.2024.265073
UR  - https://doi.org/10.51359/2965-4661.2024.265073
N2  - In this work, we develop specific models to predict the behavior of the Bitcoin cryptocurrency using a public database (Yahoo! Finance) to track price trends. The methodologies used are ARIMA and NNAR, and the validation of the models is carried out based on the daily closing values of assets. Both models fail to differ significantly. However, the adjusted model NNAR (2.2) fits slightly better with the original data series, presenting an MPE (Mean Percentage Error) of -0.102. Some prospects on the seasonality of data are discussed.
ER  -