iml: Interpretable Machine Learning

Interpretability methods to analyze the behavior and predictions of any machine learning model. Implemented methods are: Feature importance described by Fisher et al. (2018) <doi:10.48550/arxiv.1801.01489>, accumulated local effects plots described by Apley (2018) <doi:10.48550/arxiv.1612.08468>, partial dependence plots described by Friedman (2001) <>, individual conditional expectation ('ice') plots described by Goldstein et al. (2013) <doi:10.1080/10618600.2014.907095>, local models (variant of 'lime') described by Ribeiro et. al (2016) <doi:10.48550/arXiv.1602.04938>, the Shapley Value described by Strumbelj et. al (2014) <doi:10.1007/s10115-013-0679-x>, feature interactions described by Friedman et. al <doi:10.1214/07-AOAS148> and tree surrogate models.

Version: 0.11.3
Imports: checkmate, data.table, Formula, future, future.apply, ggplot2, Metrics, R6
Suggests: ALEPlot, bench, bit64, caret, covr, e1071, future.callr, glmnet, gower, h2o, keras (≥, knitr, MASS, mlr, mlr3, party, partykit, patchwork, randomForest, ranger, rmarkdown, rpart, testthat, yaImpute
Published: 2024-04-27
DOI: 10.32614/CRAN.package.iml
Author: Giuseppe Casalicchio [aut, cre], Christoph Molnar [aut], Patrick Schratz ORCID iD [aut]
Maintainer: Giuseppe Casalicchio <giuseppe.casalicchio at>
License: MIT + file LICENSE
NeedsCompilation: no
Citation: iml citation info
Materials: NEWS
In views: MachineLearning
CRAN checks: iml results


Reference manual: iml.pdf
Vignettes: Introduction to iml: Interpretable Machine Learning in R
Parallel computation of interpretation methods


Package source: iml_0.11.3.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): iml_0.11.3.tgz, r-oldrel (arm64): iml_0.11.3.tgz, r-release (x86_64): iml_0.11.3.tgz, r-oldrel (x86_64): iml_0.11.3.tgz
Old sources: iml archive

Reverse dependencies:

Reverse imports: counterfactuals, FACT, moreparty
Reverse suggests: DALEXtra, explainer, mistyR, mlr3fairness, mlr3summary, tidyfit


Please use the canonical form to link to this page.