Forecasting commodity prices in Brazil through hybrid SSA-complex seasonality models

Paper aims To predict monthly corn, soybean, and sugar spot prices in Brazil using hybrid forecasting techniques. Originality This study combines the Singular Spectrum Analysis with different methods. Research method paper presents a set of approaches combining (SSA) univariate time series methods, ranging from complex seasonality methods to machine learning autoregressive models Brazil. We carry out range out-of-sample experiments use comprehensive forecast evaluation metrics. contrast performance proposed that benchmark models. Main findings The results show present better performances, SSA-neural network approach providing most competitive our sample. Implications for theory practice Forecasting agricultural is paramount importance assist producers, farmers, industry decision-making processes.