Performance comparison
| Model | Without SESTM | With SESTM |
|---|---|---|
| Panel A. R-square comparison | ||
| LGBM | 0.060 | 0.300 |
| CB | 0.070 | 0.330 |
| RF | 0.070 | 0.370 |
| LR | 0.170 | 0.310 |
| Panel B. RMSE comparison | ||
| LGBM | 0.040 | 0.020 |
| CB | 0.040 | 0.010 |
| RF | 0.040 | 0.010 |
| LR | 0.040 | 0.020 |
| Panel C. MAE comparison | ||
| LGBM | 0.030 | 0.030 |
| CB | 0.030 | 0.030 |
| RF | 0.030 | 0.020 |
| LR | 0.020 | 0.020 |
| Panel D. QLIKE comparison | ||
| LGBM | 0.009 | 0.007 |
| CB | 0.011 | 0.006 |
| RF | 0.012 | 0.007 |
| LR | 0.008 | 0.005 |
| Model | Without SESTM | With SESTM |
|---|---|---|
| Panel A. | ||
| LGBM | 0.060 | 0.300 |
| CB | 0.070 | 0.330 |
| RF | 0.070 | 0.370 |
| LR | 0.170 | 0.310 |
| Panel B. RMSE comparison | ||
| LGBM | 0.040 | 0.020 |
| CB | 0.040 | 0.010 |
| RF | 0.040 | 0.010 |
| LR | 0.040 | 0.020 |
| Panel C. MAE comparison | ||
| LGBM | 0.030 | 0.030 |
| CB | 0.030 | 0.030 |
| RF | 0.030 | 0.020 |
| LR | 0.020 | 0.020 |
| Panel D. QLIKE comparison | ||
| LGBM | 0.009 | 0.007 |
| CB | 0.011 | 0.006 |
| RF | 0.012 | 0.007 |
| LR | 0.008 | 0.005 |
Note(s): This table summarizes the performance evaluation of ML forecasting models. Four ML models are used: Light Gradient Boosting Machine (LGBM), Categorical Boosting (CB), Random Forest (RF), and Linear Regression (LR). Panel A represents the R-square results, Panel B displays the Root Mean Squared Error (RMSE), Panel C shows the Mean Absolute Error (MAE), and Panel D reports the Quasi-Likelihood (QLIKE)
Source(s): Authors’ own work
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.