Table 9

Performance comparison

ModelWithout SESTMWith SESTM
Panel A. R-square comparison
LGBM0.0600.300
CB0.0700.330
RF0.0700.370
LR0.1700.310
Panel B. RMSE comparison
LGBM0.0400.020
CB0.0400.010
RF0.0400.010
LR0.0400.020
Panel C. MAE comparison
LGBM0.0300.030
CB0.0300.030
RF0.0300.020
LR0.0200.020
Panel D. QLIKE comparison
LGBM0.0090.007
CB0.0110.006
RF0.0120.007
LR0.0080.005

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

or Create an Account

Close subscription notice
Close access options