Press "Enter" to skip to content

Interpreting Kernel SHAP

Michael Mayer digs into Kernel SHAP:

In their 2017 paper on SHAP, Scott Lundberg and Su-In Lee presented Kernel SHAP, an algorithm to calculate SHAP values for any model with numeric predictions. Compared to Monte-Carlo sampling (e.g. implemented in R package “fastshap”), Kernel SHAP is much more efficient.

I had one problem with Kernel SHAP: I never really understood how it works!

Needless to say, Michael knows Kernel SHAP a lot better now, considering there’s now a kernelshap package for us.