Individual conditional expectation curves for the model accuracy. Each blue line represents the accuracy of the model depending on the chosen value for each hyperparameter. The orange dashed line indicates the mean accuracy value, approximately 0.98, which is below the median accuracy value, closer to 0.99. The red dashed line represents the performance of a Random Forest Regressor with 500 trees. Most hyperparameters have minimal impact on model performance, except for the Dropout at L₀, and the number of neurons at levels L_1–4.