You've trained a model that looks strong on the training set, but the validation score is noticeably worse. The team wants to know whether the gap means the model is overfitting.
How do you validate that a model is not overfitting?
You've trained a model that looks strong on the training set, but the validation score is noticeably worse. The team wants to know whether the gap means the model is overfitting.
How do you validate that a model is not overfitting?