Influence of hyperparameter tuning on the performance of the Boosted Ensemble (BE) classification model. The plots display the relationship between key hyperparameters (i.e. tree depth, learn rate and sample size) and model performance, measured through Area Under the Precision-Recall Curve (AUPRC). The results indicate that performance improves with deeper trees and moderate learning rates up to an optimal threshold, beyond which accuracy stabilies or slightly declines, suggesting diminishing returns and potential overfitting.