ROC Curve and AUC Instructions:Number of questions: 8Time limit: 20 minutesMust be finished in one sitting. You cannot save and finish later.Questions displayed per page: 1Will allow you to go back and change your answers.Will not let you finish with any questions unattempted. 1 / 8 What is the definition of the ROC curve? A plot of precision versus sensitivity (recall) A plot of precision versus specificity A plot of sensitivity (recall) versus specificity A plot of accuracy versus specificity A plot of accuracy versus sensitivity (recall) 2 / 8 What is the definition of the AUC? AUC is the total area over the ROC curve AUC is the total area under the ROC curve AUC is a part of area over the ROC curve AUC is a part of area under the ROC curve 3 / 8 Which option is correct about the ROC curve? You can see that there is a tradeoff between recall and specificity The ROC curve plots sensitivity (recall) on the y-axis against specificity on the x-axis The ideal classifier would classify the 1s without misclassifying more 0s as 1s The ROC curves are especially useful in evaluating data with highly unbalanced outcomes All of the above 4 / 8 The plot below is a ROC curve of a model. What is the recall in this case if we want a classifier with a specificity of at least 50%? 50% 25% 100% 75% 0% 5 / 8 Which option is incorrect about AUC? AUC stands for Area Underneath the Curve The larger the value of AUC, the more effective the classifier An AUC of 1 indicates a perfect classifier, which means it gets all the 1s correctly classified, and doesn’t misclassify any 0s as 1s A completely effective classifier is a diagonal line, and it will have an AUC of 0.5 None of the above 6 / 8 Which is the possible value of AUC for the ROC curve below? 0.69 0.5 0.45 0.31 0.25 7 / 8 According to the ROC curve and AUC below, which answer is correct in terms of an effective classifier? A = B A < B A > B None of the above 8 / 8 Costco is using a Computer Vision application to detect whether customers wear face masks or not. You as a Data Scientist, got a ROC curve and AUC of the classifier. Our goal is to get as high as possible on successfully detecting customers who do not wear face masks (Ture Positive) and get as low as possible on False Negative. According to the goal, which threshold on the ROC curve should we take? A B C D E F G H Your score is 0% Restart quiz
