Abstract
Forecasts of spot or future prices for agricultural commodities make it possible to anticipate the favorableor above all unfavorable development of future profits from the exploitation of agricultural farmsor agri-food enterprises. Previous research has shown that cyclical behavior is a dominant featureof the time series of prices of certain agricultural commodities, which may be affected by a seasonalcomponent. Wavelet analysis makes it possible to capture this cyclicity by decomposing a time seriesinto its frequency and time domains. This paper proposes a time-frequency decomposition based approachto choose a seasonal auto-regressive aggregate (SARIMA) model for forecasting the monthlyprices of certain agricultural futures prices. The originality of the proposed approach is due to theidentification of the optimal combination of the wavelet transformation type, the wavelet function andthe number of decomposition levels used in the multi-resolution approach (MRA), that significantlyincrease the accuracy of the forecast. Our SARIMA hybrid approach contributes to take into accountthe cyclicity and of the seasonality when predicting commodity prices. As a relevant result, our studyallows an economic agent, according to his forecasting horizon, to choose according to the availabledata, a specific SARIMA process for forecasting.