Table 8 Hyperparameters of the XGBoost regression model.
Hyperparameter | Description | Value | Hyperparameter |
|---|---|---|---|
n_estimators | Number of trees to be trained in the model, i.e., the number of boosting iterations. | 250 | n_estimators |
max_depth | Maximum depth of each tree. | 5 | max_depth |
learning_rate | Learning rate controlling the contribution of each tree to the final result. | 0.03 | learning_rate |
random_state | Random seed to ensure reproducibility of results. | 29 | random_state |
reg_lambda | L2 regularization coefficient. | 6 | reg_lambda |
gamma | Minimum loss reduction required to make a further partition on a leaf node. | 0.5 | gamma |
colsample_bytree | Fraction of features to be randomly sampled for each tree. | 0.7 | colsample_bytree |
subsample | Fraction of training samples to be randomly drawn (without replacement) for each tree. | 0.79 | subsample |
min_child_weight | Minimum sum of instance weight (Hessian) required in a child node. | 20 | min_child_weight |
