1
$\begingroup$

For example, if I have a sample with a decision score of -6 and another with a score of -3, which sample is closer to the hyperplane?

Also, does the probability of a sample belonging to a class increase with its respective distance from the hyperplane (larger distance from hyperplane = larger probability)?

I am using sklearn's decision_function and predict_proba functions to get these values if it makes a difference.

Thanks.

$\endgroup$
1
$\begingroup$

Larger scores do mean farther from the separating hyperplane.

The SVM model itself isn't modeling probability, so you can't quite say that farther points are considered more probably in one class or the other by the model. There are ways to estimate a probability (see the scikit implementation) for example and yes it will generally be true if so that farther points are more certain, according to that estimate.

| improve this answer | |
$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.