0
$\begingroup$

I am running several machine learning classifiers to predict something from my data. If I visualized the precision and recall tables as a result, is it enough to get clear idea about the proposed mdel? or do I have to consider the accuracy table in order to cover the issue?

I am running 3 different classifiers (svm, perceptron, and isolation forest) to detect anomalies in post arrays according to 3 groups of features sets extracted from the texts, so far I have the results for each classifier according to 1 and 2 features sets and 1 and 3 and for all together.

What I want to know is which classifier perform better(classify the text arrays to compromised or not ) with those combined extracted features, so far, I recognized that specific classifier with specific combined features has the highest precision value, but do I have to visualize the result of the recall and accuracy? Am I missing somehting? What precisely do you mean by "perform better"? Better in what sense?

  • perform better means which classifier has the highest accuracy in classifying the text arrays to compromised text or not.

    enter code here

$\endgroup$
  • $\begingroup$ What precisely do you mean by "perform better"? Better in what sense? $\endgroup$ – D.W. Aug 17 '17 at 23:41
  • $\begingroup$ @D.W. perform better means which classifier has the highest accuracy in classifying the text arrays to compromised text or not $\endgroup$ – Krebto Aug 18 '17 at 7:20
  • $\begingroup$ @D.W. I think the question is clear now. How about reopening the question to others instead of closing it and disappear! $\endgroup$ – Krebto Aug 22 '17 at 13:13
  • $\begingroup$ I've re-opened it, but I'm still not sure what kind of answer you are expecting or looking for. It all depends what you mean by "better". If you want to know which has the best accuracy, measure accuracy. If you want to know which has the best precision, measure precision. I'm not sure what more there is to say. $\endgroup$ – D.W. Aug 22 '17 at 17:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.