In general, I deal with imbalanced datasets in multiclass classification problems. Now I'm facing a multiclass classification problem with balanced data. In this context, are macro precision, recall, and f-measure more informative than accuracy?
$\begingroup$
$\endgroup$
12
-
$\begingroup$ What do you want to be informed about? $\endgroup$– DaveCommented Mar 28, 2023 at 12:26
-
1$\begingroup$ Sensitivity, specificity etc. and any weighted combinations of these suffer from all the same issues as accuracy, i.e., they all presume a very specific cost structure to decisions in the face of uncertainty - but they do not make the costs explicit. Better to work with probabilistic classifications and separate the decision aspect from them. Decisions need to take classifications and costs into account, and even if there are only two classes, there may well be more than two possible decisions $\endgroup$– Stephan KolassaCommented Mar 28, 2023 at 12:32
-
$\begingroup$ And that is true whether the classes are balanced or not! $\endgroup$– DaveCommented Mar 28, 2023 at 12:32
-
1$\begingroup$ @StephanKolassa, you are 100% true but might be irrelevant to the question. Sometimes there is "no" modelling, we are not presented with probabilities, but only with classification decision results. The OP did not consider any modelling particulars. $\endgroup$– ttnphnsCommented Mar 28, 2023 at 12:58
-
2$\begingroup$ @ttnphns: you make a good point. I would say that it then is even more important to think about what it means for one metric to be more useful than the other. $\endgroup$– Stephan KolassaCommented Mar 28, 2023 at 13:22
|
Show 7 more comments