Table 3 Model performance evaluation indicators.
Norm | Define | Formulas |
|---|---|---|
MSE | Mean square | \(MSE = \frac{1}{{\text{N}}}\mathop \sum \limits_{{{\text{i}} = 1}}^{{\text{N}}} ({\text{y}}({\text{i}}) - {\hat{\text{y}}}({\text{i}}))^{2}\) |
RMSE | Root mean square | \(RMSE = \sqrt {\mathop \sum \limits_{{{\text{i}} = 1}}^{{\text{N}}} ({\text{y}}({\text{i}}) - {\hat{\text{y}}}({\text{i}}))^{2} }\) |
MAE | Mean absolute value error | \(MAE = \frac{1}{{\text{N}}}\mathop \sum \limits_{{{\text{i}} = 1}}^{{\text{N}}} |{\text{y}}({\text{i}}) - {\hat{\text{y}}}({\text{i}})|\) |
MAPE | Average absolute percentage error | \(MAE = \frac{1}{{\text{N}}}\mathop \sum \limits_{{{\text{i}} = 1}}^{{\text{N}}} \left| {\frac{{{\text{y}}({\text{i}}) - {\hat{\text{y}}}({\text{i}})}}{{{\text{y}}({\text{i}})}}} \right| \times 100{\text{\% }}\) |
R2 | Coefficient of determination | \(R^{2} = 1 - \frac{{\mathop \sum \limits_{i = 1}^{N} ({\text{y}}({\text{i}}) - {\hat{\text{y}}}({\text{i}}))^{2} }}{{\mathop \sum \limits_{i = 1}^{N} ({\text{y}}({\text{i}}) - \overline{{\text{y}}} ({\text{i}}))^{2} }}\) |
