ML Interview Question: Evaluation of binary classification
Answers
-
To evaluate a classifier, one compares its output to another reference classification – ideally a perfect classification, but in practice the output of another gold standard test – and cross tabulates the data into a 2×2.
contingency table, comparing the two classifications. -
-
There are various metrics which can help in evaluation in binary class classification:
1. Confusion matrix
2. Precision Score
3. Recall Score
4. F1 Score
5. AUC/ ROC curve -
A classification metrics is a number that measures the performance that your machine learning model when it comes to assigning observations to certain classes.
Binary classification is a particular situation where you just have to classes: positive and negative.
There are various metrics which can help in evaluation in binary class classification:
1. Confusion matrix
2. Precision Score
3. Recall Score
4. F1 Score
5. AUC/ ROC curve -
There are various metrics which can help in evaluation in binary class classification:
1. Confusion matrix
2. Precision Score
3. Recall Score
4. F1 Score
5. AUC/ ROC curve
