Oil-price forecasting based on ARIMA, exponential smoothing, and autoregressive neural network models
Palavras-chave:
Exponential Smoothing, ARIMA, Forecasting, Neural Network, Oil PricesResumo
Financial time series are sensitive to exogenous shocks. From this perspective, this work presents a
comparative analysis of predictive crude oil prices scenarios, obtained from a historical series of average annual
prices. Two approaches were used: first, a combination of classic strategies based on exponential smoothing, and
ARIMA models. Second, an autoregressive neural network model. Both approaches are complementary when used
for long-term forecasting of oil prices and show good response to volatile data. Therefore, we are able to present
an alternative data analysis, in a field where there is a great amount of relevant historical series, using probabilistic
and non-linear models in order to observe predictions and make more effective decisions.
