Decision Tree Prunning 편집하기 (부분)

==Challenges with Pruning==
While pruning is effective, it also presents certain challenges:
*'''Risk of Underfitting''': Excessive pruning may remove useful splits, leading to underfitting where the model is too simple to capture the data’s complexity.
*'''Parameter Selection''': Choosing the right criteria for pruning (e.g., maximum depth, minimum samples) is crucial and may require tuning to find the optimal balance.
*'''Computational Cost in Large Trees''': Post-pruning large trees can be computationally expensive, especially in complex datasets with high dimensionality.