I have imbalance dataset for binary classification problem. I want to create a custom cost function that takes into account not only the actual class and probability, but another variable "premium amount" which is a feature in the model.

I have studied few blogs but it doesn't talk about including feature in cost function.

Kindly help!

  • 1
    $\begingroup$ I think you can just include this feature in whichever way you want in the cost function, for example f = error * premium_feature would use the feature as weight. $\endgroup$
    – Erwan
    Feb 19 at 10:28

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.