K-Nearest Neighbors (page 5 of 6)

We evaluate the quality of a KNN classification model using the confusion matrix (i.e., how often the model is confused) and other metrics based on the data in the confusion matrix. For binary classification problems, we may also use the ROC curve.



Keep in mind that we want to balance bias and variance. Often, a larger 'k' might lead to overfitting to the training data but a smaller 'k' might lead to under-fitting.

Reading Check: Opportunities don't happen, you create them.