Performance Measures

 Performance Measures

•        Evaluating a classifier is often significantly trickier than evaluating a regressor.

•        There are many performance measures available.

                           i.          Confusion Matrix

                         ii.          True Positive Rate

                       iii.          True Negative Rate

                       iv.          False Positive Rate

                         v.          False Negative Rate

                       vi.          Precision

                      vii.          Recall

                    viii.          Accuracy

                       ix.          F1-Score

                         x.          Specificity

                       xi.          Receiver Operating Characteristic (ROC)

                      xii.          Area Under Curve (AUC)

YouTube Link: https://youtu.be/jL39fMC_I28