Software Open Access

iml: An R package for Interpretable Machine Learning

Molnar, Christoph


Citation Style Language JSON Export

{
  "DOI": "10.5281/zenodo.1299059", 
  "abstract": "<p>Interpretability methods to analyze the behavior and predictions of any machine learning model.<br>\nImplemented methods are:</p>\n\n<ul>\n\t<li>Feature importance described by Fisher et al. (2018)&lt;arXiv:1801.01489&gt;</li>\n\t<li>Partial dependence plots described by Friedman (2001) &lt;http://www.jstor.org/stable/2699986&gt;</li>\n\t<li>Individual conditional expectation (&#39;ice&#39;) plots described by Goldstein et al. (2013)&lt;doi:10.1080/10618600.2014.907095&gt;</li>\n\t<li>Local models (variant of &#39;lime&#39;) described by Ribeiro et. al (2016) &lt;arXiv:1602.04938&gt;</li>\n\t<li>Shapley Value described by Strumbelj et. al (2014) &lt;doi:10.1007/s10115-013-0679-x&gt;</li>\n\t<li>Feature interactions described by Friedman et. al &lt;doi:10.1214/07-AOAS148&gt;</li>\n\t<li>Tree surrogate models.</li>\n</ul>", 
  "author": [
    {
      "family": "Molnar, Christoph"
    }
  ], 
  "id": "1299059", 
  "issued": {
    "date-parts": [
      [
        2018, 
        6, 
        27
      ]
    ]
  }, 
  "publisher": "Zenodo", 
  "title": "iml: An R package for Interpretable Machine Learning", 
  "type": "article", 
  "version": "v0.5.2"
}
133
3
views
downloads
All versions This version
Views 133133
Downloads 33
Data volume 1.6 MB1.6 MB
Unique views 131131
Unique downloads 33

Share

Cite as