kernelshap: Kernel SHAP

Multidimensional version of the iterative Kernel SHAP algorithm described in Ian Covert and Su-In Lee (2021) <>. SHAP values are calculated iteratively until convergence, along with approximate standard errors. The package allows to work with any model that provides numeric predictions of dimension one or higher. Examples include linear regression, logistic regression (logit or probability scale), other generalized linear models, generalized additive models, and neural networks. The package plays well together with meta-learning packages like 'tidymodels', 'caret' or 'mlr3'. Visualizations can be done using the R package 'shapviz'.

Version: 0.2.0
Depends: R (≥ 3.2.0)
Imports: doRNG, foreach, MASS, stats, utils
Suggests: doFuture, testthat (≥ 3.0.0)
Published: 2022-09-05
Author: Michael Mayer [aut, cre], David Watson [ctb]
Maintainer: Michael Mayer <mayermichael79 at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Materials: README NEWS
CRAN checks: kernelshap results


Reference manual: kernelshap.pdf


Package source: kernelshap_0.2.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): kernelshap_0.2.0.tgz, r-oldrel (arm64): kernelshap_0.2.0.tgz, r-release (x86_64): kernelshap_0.2.0.tgz, r-oldrel (x86_64): kernelshap_0.2.0.tgz
Old sources: kernelshap archive


Please use the canonical form to link to this page.