Correct Answer: A

Generalizing is finding pattern in order to not overfit. A model should retain its explanatory power when tested "out-of-sample". An overfit model gets a low loss during training but does a poor job predicting new data.

For overfitting, the model is too complex to fit the training data well. For underfitting, the model is too simple. It is hard to pick the "just right" model and parameters for the data.