Table 3 Meaning and function of model performance evaluation indicators.
Formula | Parameter | Meaning | Role in the model |
|---|---|---|---|
(8) (9) (10) (11) | yi | Actual observations | As the learning foundation of the model; Used for model evaluation; Reflect the real situation |
\(\overline{y}\) | Model prediction value | Test the generalization ability of the model; Provide decision support; Optimize the model | |
\(\overset{\lower0.5em\hbox{$\smash{\scriptscriptstyle\frown}$}}{y}_{i}\) | Mean of actual values | As a reference benchmark; Used for data standardization and normalization;Auxiliary model analysis | |
\(\sum\limits_{i = 1}^{N} {(\overset{\lower0.5em\hbox{$\smash{\scriptscriptstyle\frown}$}}{y}_{i} - y_{i} )^{2} }\) | Residual sum of Squares | Reflects the size of the error in model prediction | |
\(\sum\limits_{i = 1}^{N} {(y_{i} - \overline{y})^{2} }\) | Total sum of squares | Reflects the degree of fluctuation of the data itself | |
N | Number of samples | Reliability of results; Stability of indicators; Model comparative effectiveness | |
\(\overset{\lower0.5em\hbox{$\smash{\scriptscriptstyle\frown}$}}{y}_{i} - y_{i}\) | Residual | Evaluate the fitting effect of the model; Detect outliers and outliers |
