Table 9 Comparative performance metrics of forecasting models for potato prices using different sets of exogenous variables. Significant values are in bold.
From: Exogenous variable driven deep learning models for improved price forecasting of TOP crops in India
Potato | ||||||
|---|---|---|---|---|---|---|
Exogenous variables | Models | RMSE | MAE | sMAPE | MASE | QL |
Precipitation | ARIMAX | 51.966 | 37.547 | 27.659 | 1.643 | 18.773 |
MLR | 60.304 | 46.466 | 35.965 | 2.034 | 23.233 | |
ANN | 103.033 | 93.925 | 98.703 | 4.111 | 46.962 | |
SVR | 76.673 | 64.588 | 56.222 | 2.827 | 32.294 | |
RFR | 69.889 | 53.932 | 42.785 | 2.360 | 26.966 | |
XGBoost | 62.827 | 48.735 | 38.267 | 2.133 | 24.367 | |
NBEATSX | 34.099 | 21.342 | 18.897 | 0.953 | 10.671 | |
TransformerX | 34.418 | 26.773 | 19.677 | 1.221 | 13.386 | |
Temperature | ARIMAX | 52.443 | 37.613 | 27.731 | 1.646 | 18.806 |
MLR | 60.581 | 46.396 | 35.994 | 2.031 | 23.198 | |
ANN | 85.837 | 74.141 | 69.321 | 3.245 | 37.070 | |
SVR | 76.950 | 64.758 | 56.542 | 2.834 | 32.379 | |
RFR | 78.509 | 62.524 | 52.118 | 2.737 | 31.262 | |
XGBoost | 63.836 | 50.071 | 40.160 | 2.191 | 25.035 | |
NBEATSX | 33.704 | 20.761 | 18.427 | 0.927 | 10.380 | |
TransformerX | 36.329 | 27.775 | 20.149 | 1.267 | 13.887 | |
Precipitation and Temperature | ARIMAX | 52.349 | 37.525 | 27.655 | 1.642 | 18.762 |
MLR | 60.575 | 46.392 | 35.990 | 2.030 | 23.196 | |
ANN | 92.433 | 77.795 | 76.698 | 3.405 | 38.897 | |
SVR | 77.660 | 65.026 | 56.952 | 2.846 | 32.513 | |
RFR | 76.957 | 61.586 | 51.590 | 2.695 | 30.793 | |
XGBoost | 63.124 | 50.278 | 40.318 | 2.200 | 25.139 | |
NBEATSX | 34.290 | 20.737 | 18.357 | 0.926 | 10.368 | |
