For data science students, interview candidates and ML engineers evaluating a classifier. You get accuracy, precision, recall, specificity, F1 and the total sample count from the four confusion matrix cells.
Build industry projects on ByteLabs and add verified proof of your skills to your public profile.
You enter
TP 90, FP 10, FN 5, TN 95
The tool shows
Accuracy 0.925 (92.5%), precision 0.9, recall 0.9474, specificity 0.9048, F1 0.9231, 200 samples
Precision is TP divided by TP plus FP: of everything predicted positive, how much was right. Recall is TP divided by TP plus FN: of all real positives, how many were found.
On imbalanced data. If 95 percent of samples are negative, a model that always says negative gets 95 percent accuracy but an F1 of 0, so F1 shows the real performance on the positive class.
Specificity, or true negative rate, is TN divided by TN plus FP: the share of real negatives the model correctly rejected.
Yes. It is free, needs no sign-up and runs entirely in your browser, so what you type is not uploaded. You only sign in if you want to email a result to yourself or save it to your CareerByteCode profile.
