Is Facebook Prophet Superior than Hybrid Arima Model to Forecast Crude Oil Price?

Oil price forecasting has received a great deal of attention from practitioners and researchers alike, but it remains difficult topic because its dependency on variety factors, including the economic cycle, international relations, geopolitics. Forecasting oil is gratifying task. Motivated by this issue, we present robust model for accurate crude using ARIMA Prophet models based machine learning technique to produce reliable weekly monthly predictions. We apply Savitzky–Golay smoothing filter get better denoising performance our forecast models. For evaluation, cross validation with sliding windows both compares performances RMSE MAPE. The results show that ARIMA- approach performs as compared one-week one-month ahead intervals.