Table 2 Structural parameters of five ML algorithms.
Models | Parameters | Describe | Range | Values |
|---|---|---|---|---|
KNN | K | Number of neighbors participate in the KNN algorithm | 10–100 | 79 |
weights | Weight function used in prediction model | Uniform, distance | Uniform | |
SVR | C | Penalty parameter of the error term | 0.1–10 | 8 |
gamma | Kernel coefficient for radial based function | 0.001–1 | 0.001 | |
AdaBoost | base_estimator | Base estimator of the model | / | Decision tree |
n_estimators | Maximum number of estimators at which boosting is terminated | 5–500 | 100 | |
GBR | loss | Loss function to be optimized | / | Squared error |
n_estimators | The number of boosting stages to perform | 5–500 | 90 | |
max_depth | Maximum depth of the individual regression estimators | 1–10 | 3 | |
RF | base_estimator | Base estimator of the model | / | Decision tree |
n_estimators | Number of trees in the forest | 5–500 | 100 | |
max_depth | Maximum depth of the tree | 1–10 | 8 |
