Out-of-sample testing is essential for assessing a model's ability to:

A. Fit historical data.
B. Achieve high training accuracy.
C. Generalize to new, unseen data.
D. Minimize training time.

Correct Answer: C

Out-of-sample forecasting refers to the process of Testing the model on data not used during model training. Out-of-sample forecasts are usually more valuable in evaluating the forecasting performance of a time-series model than are in-sample forecasts.