In week assignment we create ROC AUC curve , I am new to this topic , can someone explain what is ROC AUC ?
I am facing problem to understand this quiz:
You have a model such that the lowest score for a positive example is higher than the maximum score for a negative example. What is its ROC AUC?
HINT 1: watch the video “Varying the threshold”.
HINT 2: draw a number line and choose values for the score that is the lowest prediction for any positive example, and choose another number that is the score for the highest prediction for any negative example. Draw a few circles for “positive” examples and a few “x” for the negative examples. What do you notice about the model’s ability to identify positive and negative examples?
There is a term named Confusion Matrix to measure the performance of a classification matrix.
AUC-ROC is another performance matrix derived from confusion matrix. It is used to measure multi-class classification model of various threshold settings. ROC shows the the probility curves and AUC shows the the area of the classes or in other words, how far separate the classes are.
This is a perfect example of the weakness of the lectures in this Specialization, particularly compared to the original Deep Learning or even the Stanford Machine Learning courses. The lecture states “ In this lesson, we’ll look at one of the most useful tools to evaluate medical models, the ROC curve…” but then doesn’t even define the acronym.
For future readers of this thread, there are some very clear definitions of ROC and AUC at this google developers page: