August 2018
Intermediate to advanced
272 pages
7h 2m
English
Classification accuracy is not a good measure, especially when we have imbalanced data. This accuracy will be more biased towards class with more data. There are many good performance evaluation metrics which provide a true picture of how an algorithm is performing such as the confusion matrix, Receiver Operating Characteristic Curve(ROC), Precision Recall (PR) curve and F1 score. These are explained in more detail later in this chapter.
Read now
Unlock full access