Table 7 Comparative performance metrics of forecasting models for tomato 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
Tomato | ||||||
|---|---|---|---|---|---|---|
Exogenous Variables | Models | RMSE | MAE | sMAPE | MASE | QL |
Precipitation | ARIMAX | 360.659 | 182.246 | 47.329 | 1.476 | 91.122 |
MLR | 365.703 | 192.737 | 52.446 | 1.561 | 96.368 | |
ANN | 435.083 | 290.909 | 132.369 | 2.356 | 145.454 | |
SVR | 372.358 | 207.38 | 61.143 | 1.679 | 103.689 | |
RFR | 368.287 | 189.698 | 51.089 | 1.536 | 94.849 | |
XGBoost | 361.723 | 190.281 | 51.792 | 1.541 | 95.140 | |
NBEATSX | 256.362 | 135.449 | 36.141 | 1.080 | 67.724 | |
TransformerX | 313.344 | 170.212 | 38.305 | 1.157 | 70.106 | |
Temperature | ARIMAX | 365.852 | 183.604 | 47.717 | 1.487 | 91.801 |
MLR | 370.087 | 193.713 | 52.543 | 1.569 | 96.856 | |
ANN | 422.271 | 265.619 | 103.662 | 2.151 | 132.809 | |
SVR | 384.234 | 212.308 | 62.890 | 1.719 | 106.153 | |
RFR | 389.481 | 223.598 | 69.728 | 1.811 | 111.799 | |
XGBoost | 366.138 | 193.418 | 53.468 | 1.566 | 96.709 | |
NBEATSX | 250.643 | 131.344 | 35.809 | 1.048 | 65.672 | |
TransformerX | 328.374 | 169.890 | 39.785 | 1.373 | 74.944 | |
Precipitation and temperature | ARIMAX | 360.724 | 182.590 | 47.527 | 1.479 | 91.295 |
MLR | 365.855 | 192.992 | 52.579 | 1.563 | 96.495 | |
ANN | 437.087 | 269.665 | 106.365 | 2.184 | 134.832 | |
SVR | 371.917 | 206.442 | 60.835 | 1.672 | 103.221 | |
RFR | 366.681 | 204.230 | 61.815 | 1.654 | 102.115 | |
XGBoost | 358.634 | 188.106 | 51.299 | 1.523 | 94.052 | |
NBEATSX | 250.293 | 130.561 | 35.605 | 1.041 | 65.280 | |
