K-Fold Cross Validation

An ensembling technique where models are trained on a different set percent of the dataset. For example each model is trained on a different 80% of the dataset.

---

Another way to think of it is that the dataset is split into \(K\) pieces. Then each model is trained on a different set of \(K-1\) pieces.

For example, let’s say that the dataset is split into 5 pieces. Then each model is trained on a different set of 4 pieces.