Track: Artificial Intelligence

Abstract

The liberalization of the petroleum sector in Morocco has a significant effect for petroleum product distributors. Since the beginning of December 2015, fuel prices are freely determined. This event presents many constraints affecting the balance of the sector plus the competition between its economic players. With the halt of the competitive manufacturing’s activity, Morocco's only refinery, distributors must, for their part, build up large stocks. As all fuel products are imported, we will be interested in the evolution by making forecasts of the price of fuels in the Moroccan market. In order to achieve their objectives, the oil companies must rely on precise forecasts. In this context, our paper aims mainly to study the time series of fuel selling price in order to provide precise forecasts to the company respecting the permissible error margin of 3%. To this end, we worked with the SVR function. The predictions made were quite satisfactory with regard to the constraint set by the company (plus or minus 3% as margin of error). The error of the SVR function used is about 2,53%. The error in then minimized compared to our previous method: ARIMA which error is about 2.855%.