0
$\begingroup$

I'm currently going through past paper questions and was wondering if I could get some help answering this one?

'Consider a classification model which is applied to a set of records, of which 100 records belong to class A (the positive class) and 900 records to class B. The model correctly predicts the class of 20 records in A and incorrectly predicts the class of 100 records in class B. Calculate the values of the confusion matrix, the accuracy, and the error rate.'

My current idea is that the 20 correctly predicted values fall into TP and the 100 values that were supposed to be in class A but were classified as class B fall into FN?

Any recommendations or ideas are much appreciated, thanks.

$\endgroup$
4
  • 2
    $\begingroup$ Try wikipidea? en.wikipedia.org/wiki/Confusion_matrix $\endgroup$
    – bigbang
    Commented Apr 30, 2021 at 20:30
  • $\begingroup$ I've already been over this and other sources. I just need clarification regarding the current approach I have tried. Thanks for the useless feedback of copy and pasting links. $\endgroup$ Commented May 3, 2021 at 12:19
  • $\begingroup$ We encourage you to show the research you've done, summarize what you've found so far, and tell us why you've rejected it. Otherwise, we have no way to know what sources you've already looked at and why they weren't sufficient. You seem to suggest an approach; why do you doubt it? The more you give us to work with, the more likely that we can help you. We discourage "here is an exercise-style question, how do I solve it?", as that's unlikely to help others in the future. $\endgroup$
    – D.W.
    Commented May 4, 2021 at 3:51
  • $\begingroup$ Also please ask only one question per post -- I see three separate questions here, specifically, how to compute the confusion matrix, how to compute the accuracy, and how to compute the error rate. $\endgroup$
    – D.W.
    Commented May 4, 2021 at 3:52

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.