Model interpretation has been an important area of study nowadays and because of that some different techniques have risen to help on this task. Maybe the two most famous ones are LIME and SHAP.

How would you explain the main differences between the two methods in a simple way?

And in which situations one method would maybe be better suited than the other?

  • $\begingroup$ I would guess that the fact that SHAP is based on game theory is maybe an important particularity that can derive important (and different) comprehensions regarding other methods like LIME, but I'm not so sure on which other important details they can be separated apart from each other. $\endgroup$ Commented Dec 4, 2018 at 21:16
  • 1
    $\begingroup$ Partially answered: stats.stackexchange.com/questions/379744/… $\endgroup$ Commented Dec 19, 2018 at 13:09


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.