Classification and ROC Flashcards
How is accuracy of classification model estimated?
confusion matrix
what is Accuracy
How often are prediction correct overall
TP+TN/ ALL
What is Precision?
When prediction were yes/positive , how often are they correct?
TP / (TP + FP)
what is recall?
When actuals were yes or positive, how often are they correct?
TP / (TP + FN)
What is goal of Cross validation like k-fold.
The goal of cross-validation is to test the model’s ability to predict new data that was not used in estimating it
What are Estimation methodologies for classification?
K-Fold cross validation
Leave-one-out
bootstrapping
jackknifing
Area under the ROC curve
What is ROC curve
ROC(Receiver Operating Characteristic)
for visual comparison of classification models
what does area under the ROC curve measure?
the area under the ROC curve measures the accuracy of the model.
What does ROC curve shows? in terms of confusion matrics
shows trade-off between the true positive rate and the false positive rate.
what is the area of curve of perfect accuracy?
1
what is k-fold cross validation
Estimation methodology for classification.
spilts the data into K mutually exclusive subsets.
