Which of the following is the PRIMARY advantage of using K-fold cross validation when evaluating...

The primary advantage of K-fold cross validation is that it uses multiple train/test splits, cycling through all folds so that each observation is used both for training and testing at different points. This process provides a more reliable estimate of model performance and reduces the risk of overfitting to a single split (option D). It is an established best practice in model evaluation and aligns with AAIA’s emphasis on testing techniques for AI solutions and data analytics .

Option A is not specific to regressions; cross validation can be used for classification and other models as well. Option B can actually increase computational cost since multiple models are trained. Option C misunderstands bias–variance trade-offs; increasing K doesn’t simply “reduce model bias.” The key advantage remains the use of repeated, varied splits to better assess generalization and guard against overfitting.