Working Papers

Forecasting the Brazilian light fuel consumption using time series and machine learning techniques

In this paper, we evaluate different methods for making predictions about the consumption of light fuels in Brazil. The analysis recognizes the need to anticipate the behavior of demand, considered as one of the main elements associated with greater predictability to the fuel market. The study seeks to fill a gap in the literature on the Brazilian light fuel market. In addition, the methodological strategy adopted assesses projection models from different areas of knowledge using a robust evaluation procedure.