{"id":184144,"date":"2024-05-01T03:26:00","date_gmt":"2024-05-01T02:26:00","guid":{"rendered":"https:\/\/datascientest.com\/en\/?p=184144"},"modified":"2024-04-01T15:50:13","modified_gmt":"2024-04-01T14:50:13","slug":"shap-interpreting-ai-models","status":"publish","type":"post","link":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models","title":{"rendered":"SHAP: interpreting AI models"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"184144\" class=\"elementor elementor-184144\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-d36ffab e-flex e-con-boxed e-con\" data-id=\"d36ffab\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-d66a3ea elementor-widget elementor-widget-heading\" data-id=\"d66a3ea\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h2 class=\"elementor-heading-title elementor-size-default\">The ability to understand and explain the decisions taken by Artificial Intelligence or Machine Learning models has become essential. These sophisticated technologies are increasingly being integrated into critical areas such as health, finance and security. Solutions like SHAP (SHapley Additive exPlanations) are booming.<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-959c138 elementor-widget elementor-widget-text-editor\" data-id=\"959c138\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<p>SHAP is inspired by the concepts of cooperative game theory, and offers a rigorous and intuitive method for decomposing model predictions into the individual contributions of each feature.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1a0360b elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"1a0360b\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/en\/machine-learning-engineer-course\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Learn all about SHAP<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-d471f84 e-flex e-con-boxed e-con\" data-id=\"d471f84\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-fe4ab7a elementor-widget elementor-widget-heading\" data-id=\"fe4ab7a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Theoretical foundations of SHAP<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0e2dc22 elementor-widget elementor-widget-text-editor\" data-id=\"0e2dc22\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>It is necessary to analyse the <strong>theoretical roots of SHAP<\/strong> in order to understand its added value, but also the reason why it is effective in interpreting sometimes complex models.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-a595904 e-flex e-con-boxed e-con\" data-id=\"a595904\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-513da89 e-con-full e-flex e-con\" data-id=\"513da89\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-bc6b061 elementor-widget elementor-widget-image\" data-id=\"bc6b061\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/01\/image1-2.png\" title=\"\" alt=\"\" loading=\"lazy\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-513e257 e-con-full e-flex e-con\" data-id=\"513e257\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-64343b1 elementor-widget elementor-widget-heading\" data-id=\"64343b1\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Cooperative game theory<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e6416da elementor-widget elementor-widget-text-editor\" data-id=\"e6416da\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>This theory, a branch of<strong> game theory<\/strong>, focuses on the analysis of strategies for groups of agents who can form coalitions and share rewards. At the heart of this theory is the notion of &#8216;fair value&#8217;, a way of distributing gains (or losses) among participants in a way that reflects their individual contribution. It is in this context that Shapley&#8217;s Value.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-407de48 e-flex e-con-boxed e-con\" data-id=\"407de48\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-cbb49d4 e-con-full e-flex e-con\" data-id=\"cbb49d4\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-86c6fc3 elementor-widget elementor-widget-image\" data-id=\"86c6fc3\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/01\/image1-2.png\" title=\"\" alt=\"\" loading=\"lazy\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-91f2788 e-con-full e-flex e-con\" data-id=\"91f2788\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-3bbfda5 elementor-widget elementor-widget-heading\" data-id=\"3bbfda5\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Cooperative game theory<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-39dc692 elementor-widget elementor-widget-text-editor\" data-id=\"39dc692\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>This theory, a branch of game theory, focuses on the analysis of strategies for groups of agents who can form coalitions and share rewards. At the heart of this theory is the notion of &#8216;fair value&#8217;, a way of <strong>distributing gains (or losses) among participants i<\/strong>n a way that reflects their individual contribution. It is in this context that Shapley&#8217;s Value.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-9d02324 e-flex e-con-boxed e-con\" data-id=\"9d02324\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-45f4653 e-con-full e-flex e-con\" data-id=\"45f4653\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-0a570fd elementor-widget elementor-widget-image\" data-id=\"0a570fd\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/01\/image6-2.png\" title=\"\" alt=\"\" loading=\"lazy\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-903df7b e-con-full e-flex e-con\" data-id=\"903df7b\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-8179a23 elementor-widget elementor-widget-heading\" data-id=\"8179a23\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Shapley Value<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3d9c065 elementor-widget elementor-widget-text-editor\" data-id=\"3d9c065\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>This is a <a href=\"https:\/\/datascientest.com\/en\/sequences-and-series-understanding-these-two-mathematical-concepts\">mathematical concept<\/a>, introduced by Lloyd Shapley in 1953, used to determine the fair share of each player in a cooperative game. It is calculated by considering all possible permutations of players and evaluating the marginal impact of each player when he joins a coalition. In other words, it measures the average contribution of a player to the coalition, taking into account all the possible combinations in which that player could contribute.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-d90e6c2 e-flex e-con-boxed e-con\" data-id=\"d90e6c2\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-2c4f672 e-con-full e-flex e-con\" data-id=\"2c4f672\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-b2c6b60 elementor-widget elementor-widget-image\" data-id=\"b2c6b60\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/01\/image5-3.png\" title=\"\" alt=\"\" loading=\"lazy\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-2c53db6 e-con-full e-flex e-con\" data-id=\"2c53db6\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;full&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-0cb5ad2 elementor-widget elementor-widget-heading\" data-id=\"0cb5ad2\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Link with SHAP<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c37815c elementor-widget elementor-widget-text-editor\" data-id=\"c37815c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>In the context of machine learning, <strong>SHAP uses the Shapley Value<\/strong> to assign an &#8220;importance value&#8221; to each feature of a predictive model. Each feature of a data instance is considered as a &#8220;player&#8221; in a cooperative game where the &#8220;payoff&#8221; is the <a href=\"https:\/\/datascientest.com\/en\/shap-what-is-it\">prediction of the model.<\/a><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-13bb049 e-flex e-con-boxed e-con\" data-id=\"13bb049\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-3cac85a elementor-widget elementor-widget-heading\" data-id=\"3cac85a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">How does SHAP work?<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8784a36 elementor-widget elementor-widget-text-editor\" data-id=\"8784a36\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>At the heart of SHAP is the idea of decomposing a specific prediction into a set of values assigned to each input feature. These values are calculated to reflect the impact of each feature on the difference between the current prediction and the average prediction over the data set. To achieve this, SHAP explores all possible combinations of features and their contributions to the prediction. This process uses the Shapley Value, discussed earlier, to ensure a fair and accurate distribution of impact across features.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d9d806c elementor-widget elementor-widget-heading\" data-id=\"d9d806c\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Let's take an example<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1794b49 elementor-widget elementor-widget-text-editor\" data-id=\"1794b49\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Imagine a predictive model used in the financial sector to assess credit risk. SHAP can reveal how characteristics such as credit score, annual income and repayment history contribute to the model&#8217;s final decision. If a customer is refused credit, SHAP can indicate which characteristics most influenced this negative decision, providing relevant indicators.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4cb59d0 elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"4cb59d0\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/en\/machine-learning-engineer-course\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Understanding how SHAP works<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-bdf92ab e-flex e-con-boxed e-con\" data-id=\"bdf92ab\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-518a241 elementor-widget elementor-widget-heading\" data-id=\"518a241\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Using Python<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e1bdca9 elementor-widget elementor-widget-text-editor\" data-id=\"e1bdca9\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Python provides a library for SHAP. This allows users to take full advantage of SHAP for model interpretability.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d2a914c elementor-widget elementor-widget-heading\" data-id=\"d2a914c\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Installation<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-540602c elementor-widget elementor-widget-text-editor\" data-id=\"540602c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>The first step, of course, is to install the library<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-9eab603 elementor-widget elementor-widget-code-highlight\" data-id=\"9eab603\" data-element_type=\"widget\" data-widget_type=\"code-highlight.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"prismjs-default copy-to-clipboard word-wrap\">\n\t\t\t<pre data-line=\"\" class=\"highlight-height language-python \">\n\t\t\t\t<code readonly=\"true\" class=\"language-python\">\n\t\t\t\t\t<xmp>pip install shap<\/xmp>\n\t\t\t\t<\/code>\n\t\t\t<\/pre>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c3b7781 elementor-widget elementor-widget-text-editor\" data-id=\"c3b7781\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Once installed, all you need to do is import it into your environment:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-795f344 elementor-widget elementor-widget-code-highlight\" data-id=\"795f344\" data-element_type=\"widget\" data-widget_type=\"code-highlight.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"prismjs-default copy-to-clipboard word-wrap\">\n\t\t\t<pre data-line=\"\" class=\"highlight-height language-python \">\n\t\t\t\t<code readonly=\"true\" class=\"language-python\">\n\t\t\t\t\t<xmp>import shap<\/xmp>\n\t\t\t\t<\/code>\n\t\t\t<\/pre>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-df1d46c elementor-widget elementor-widget-heading\" data-id=\"df1d46c\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Data preparation<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-20e2b90 elementor-widget elementor-widget-text-editor\" data-id=\"20e2b90\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Suppose you have a Machine Learning model that has already been trained, such as a random forest model for classification (RandomForestClassifier). You will then need a dataset for analysis:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ec19942 elementor-widget elementor-widget-code-highlight\" data-id=\"ec19942\" data-element_type=\"widget\" data-widget_type=\"code-highlight.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"prismjs-default copy-to-clipboard word-wrap\">\n\t\t\t<pre data-line=\"\" class=\"highlight-height language-python \">\n\t\t\t\t<code readonly=\"true\" class=\"language-python\">\n\t\t\t\t\t<xmp>from sklearn.model_selection import train_test_split\r\nfrom sklearn.ensemble import RandomForestClassifier\r\nimport pandas as pd\r\n\r\n# Load and prepare datas\r\ndata = pd.read_csv('my_amazing_dataset.csv')\r\nX = data.drop('target', axis=1)\r\ny = data['target']\r\n\r\n# Split train and test set\r\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\r\n\r\n# Train the model\r\nmodel = RandomForestClassifier(random_state=42)\r\nmodel.fit(X_train, y_train)<\/xmp>\n\t\t\t\t<\/code>\n\t\t\t<\/pre>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f1f164d elementor-widget elementor-widget-heading\" data-id=\"f1f164d\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Analyse SHAP<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-62b1f4e elementor-widget elementor-widget-text-editor\" data-id=\"62b1f4e\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Once the model has been trained, you can use SHAP to analyse the impact of the characteristics. To continue this example, we can use the Explainer Tree.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6b033ff elementor-widget elementor-widget-code-highlight\" data-id=\"6b033ff\" data-element_type=\"widget\" data-widget_type=\"code-highlight.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"prismjs-default copy-to-clipboard word-wrap\">\n\t\t\t<pre data-line=\"\" class=\"highlight-height language-python \">\n\t\t\t\t<code readonly=\"true\" class=\"language-python\">\n\t\t\t\t\t<xmp># Create Explainer Tree\r\nexplainer = shap.TreeExplainer(model)\r\n\r\n# Compute SHAP Values on the test set\r\nshap_values = explainer.shap_values(X_test)<\/xmp>\n\t\t\t\t<\/code>\n\t\t\t<\/pre>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1ee5ea2 elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"1ee5ea2\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/en\/machine-learning-engineer-course\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Learn how to use SHAP<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-da911b5 elementor-widget elementor-widget-heading\" data-id=\"da911b5\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-medium\">Viewing results<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-99b3beb elementor-widget elementor-widget-text-editor\" data-id=\"99b3beb\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>SHAP naturally offers various visualisation options for interpreting the results. For example, for a summary of the importance of :<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-11c63ea elementor-widget elementor-widget-code-highlight\" data-id=\"11c63ea\" data-element_type=\"widget\" data-widget_type=\"code-highlight.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"prismjs-default copy-to-clipboard word-wrap\">\n\t\t\t<pre data-line=\"\" class=\"highlight-height language-python \">\n\t\t\t\t<code readonly=\"true\" class=\"language-python\">\n\t\t\t\t\t<xmp>shap.summary_plot(shap_values, X_test)<\/xmp>\n\t\t\t\t<\/code>\n\t\t\t<\/pre>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f0871cf elementor-widget elementor-widget-image\" data-id=\"f0871cf\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t<figure class=\"wp-caption\">\n\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/01\/image7-2.png\" title=\"\" alt=\"\" loading=\"lazy\" \/>\t\t\t\t\t\t\t\t\t\t\t<figcaption class=\"widget-image-caption wp-caption-text\"><\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4dda615 elementor-widget elementor-widget-text-editor\" data-id=\"4dda615\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>It is also possible to examine the impact of a specific characteristic:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-249d013 elementor-widget elementor-widget-code-highlight\" data-id=\"249d013\" data-element_type=\"widget\" data-widget_type=\"code-highlight.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"prismjs-default copy-to-clipboard word-wrap\">\n\t\t\t<pre data-line=\"\" class=\"highlight-height language-python \">\n\t\t\t\t<code readonly=\"true\" class=\"language-python\">\n\t\t\t\t\t<xmp># Need to initialize javascript in order to display the plots\r\nshap.initjs()\r\n\r\n# View impact\r\nshap.plots.force(explainer.expected_value[0], shap_values[0])<\/xmp>\n\t\t\t\t<\/code>\n\t\t\t<\/pre>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c691d55 elementor-widget elementor-widget-image\" data-id=\"c691d55\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t<figure class=\"wp-caption\">\n\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2024\/01\/image4-2.png\" title=\"\" alt=\"\" loading=\"lazy\" \/>\t\t\t\t\t\t\t\t\t\t\t<figcaption class=\"widget-image-caption wp-caption-text\"><\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-037e3e2 e-flex e-con-boxed e-con\" data-id=\"037e3e2\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-78b20a6 elementor-widget elementor-widget-heading\" data-id=\"78b20a6\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">In conclusion<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4ec7580 elementor-widget elementor-widget-text-editor\" data-id=\"4ec7580\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>SHAP (SHapley Additive exPlanations)<\/strong> is a powerful and versatile tool for the interpretability of <a href=\"https:\/\/datascientest.com\/en\/data-poisoning-a-threat-to-machine-learning-models\">Machine Learning models<\/a>. Drawing on the principles of cooperative game theory and Shapley Value, it provides a rigorous method for decomposing and understanding the contributions of individual features to a model&#8217;s predictions.<\/p><p>The use of the SHAP <a href=\"https:\/\/datascientest.com\/en\/pycaret-everything-you-need-to-know-about-this-python-library\">library in Python<\/a> demonstrates its ease of integration and implementation in the data science workflow. What&#8217;s more, with Artificial Intelligence becoming increasingly ubiquitous, the interpretability of models cannot afford to be underestimated.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d1ba33c elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"d1ba33c\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/en\/machine-learning-engineer-course\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Learn to use SHAP<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c12accb elementor-widget elementor-widget-html\" data-id=\"c12accb\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script type=\"application\/ld+json\">\n{\n  \"@context\": \"https:\/\/schema.org\",\n  \"@type\": \"FAQPage\",\n  \"mainEntity\": [{\n    \"@type\": \"Question\",\n    \"name\": \"What is SHAP?\",\n    \"acceptedAnswer\": {\n      \"@type\": \"Answer\",\n      \"text\": \"SHAP draws on concepts from cooperative game theory, and provides a rigorous and intuitive method for decomposing model predictions into the individual contributions of each feature.\"\n    }\n  },{\n    \"@type\": \"Question\",\n    \"name\": \"Why SHAP?\",\n    \"acceptedAnswer\": {\n      \"@type\": \"Answer\",\n      \"text\": \"The ability to understand and explain the decisions made by Artificial Intelligence or Machine Learning models has become essential. These sophisticated technologies are increasingly being integrated into critical areas such as health, finance and security. Solutions such as SHAP (SHapley Additive exPlanations) are booming.\"\n    }\n  },{\n    \"@type\": \"Question\",\n    \"name\": \"How does SHAP work?\",\n    \"acceptedAnswer\": {\n      \"@type\": \"Answer\",\n      \"text\": \"At the heart of SHAP is the idea of decomposing a specific prediction into a set of values assigned to each input feature. These values are calculated to reflect the impact of each feature on the difference between the current prediction and the average prediction over the data set. To achieve this, SHAP explores all possible combinations of features and their contributions to the prediction. This process uses Shapley's Value, which we discussed earlier, to ensure a fair and accurate distribution of impact across features.\"\n    }\n  }]\n}\n<\/script>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>The ability to understand and explain the decisions taken by Artificial Intelligence or Machine Learning models has become essential. These sophisticated technologies are increasingly being integrated into critical areas such as health, finance and security. Solutions like SHAP (SHapley Additive exPlanations) are booming. SHAP is inspired by the concepts of cooperative game theory, and offers [&hellip;]<\/p>\n","protected":false},"author":67,"featured_media":184147,"comment_status":"open","ping_status":"open","sticky":false,"template":"elementor_theme","format":"standard","meta":{"content-type":"","inline_featured_image":false},"categories":[46],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.7 (Yoast SEO v21.7) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>SHAP: interpreting AI models<\/title>\n<meta name=\"description\" content=\"SHAP (SHapley Additive exPlanations) is a powerful tool for interpreting machine learning models, including but not...\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"SHAP: interpreting AI models\" \/>\n<meta property=\"og:description\" content=\"The ability to understand and explain the decisions taken by Artificial Intelligence or Machine Learning models has become essential. These sophisticated\" \/>\n<meta property=\"og:url\" content=\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models\" \/>\n<meta property=\"og:site_name\" content=\"Data Science Courses | DataScientest\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DataScientestEN\" \/>\n<meta property=\"article:published_time\" content=\"2024-05-01T02:26:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-01T14:50:13+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/datascientest.com\/en\/files\/2024\/05\/SHAP_datascientest-768x439-1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"768\" \/>\n\t<meta property=\"og:image:height\" content=\"439\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Melanie\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DataScientest__\" \/>\n<meta name=\"twitter:site\" content=\"@DataScientest__\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Melanie\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models#article\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models\"},\"author\":{\"name\":\"Melanie\",\"@id\":\"https:\/\/datascientest.com\/en\/#\/schema\/person\/19d5f7ade9407eb69af3bf6d1ae1731d\"},\"headline\":\"SHAP: interpreting AI models\",\"datePublished\":\"2024-05-01T02:26:00+00:00\",\"dateModified\":\"2024-04-01T14:50:13+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models\"},\"wordCount\":745,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/en\/#organization\"},\"articleSection\":[\"Non class\u00e9\"],\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models#respond\"]}],\"copyrightYear\":\"2024\",\"copyrightHolder\":{\"@id\":\"https:\/\/datascientest.com\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models\",\"url\":\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models\",\"name\":\"SHAP: interpreting AI models\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/en\/#website\"},\"datePublished\":\"2024-05-01T02:26:00+00:00\",\"dateModified\":\"2024-04-01T14:50:13+00:00\",\"description\":\"SHAP (SHapley Additive exPlanations) is a powerful tool for interpreting machine learning models, including but not...\",\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/datascientest.com\/en\/#website\",\"url\":\"https:\/\/datascientest.com\/en\/\",\"name\":\"Data Science Courses | DataScientest\",\"description\":\"Leader in Data Science Courses\",\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/en\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/datascientest.com\/en\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/datascientest.com\/en\/#organization\",\"name\":\"DataScientest\",\"url\":\"https:\/\/datascientest.com\/en\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/datascientest.com\/en\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/datascientest.com\/en\/wp-content\/blogs.dir\/9\/files\/2024\/02\/DataScientest_icon_blue-2.png\",\"contentUrl\":\"https:\/\/datascientest.com\/en\/wp-content\/blogs.dir\/9\/files\/2024\/02\/DataScientest_icon_blue-2.png\",\"width\":301,\"height\":301,\"caption\":\"DataScientest\"},\"image\":{\"@id\":\"https:\/\/datascientest.com\/en\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/DataScientestEN\",\"https:\/\/twitter.com\/DataScientest__\",\"https:\/\/www.linkedin.com\/school\/datascientest\/mycompany\/\",\"https:\/\/www.tiktok.com\/@datascientest\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/datascientest.com\/en\/#\/schema\/person\/19d5f7ade9407eb69af3bf6d1ae1731d\",\"name\":\"Melanie\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/datascientest.com\/en\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/8d3d660a0698de06f13ecf4823519da1?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/8d3d660a0698de06f13ecf4823519da1?s=96&d=mm&r=g\",\"caption\":\"Melanie\"},\"url\":\"https:\/\/datascientest.com\/en\/author\/melaniekrause\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"SHAP: interpreting AI models","description":"SHAP (SHapley Additive exPlanations) is a powerful tool for interpreting machine learning models, including but not...","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models","og_locale":"en_GB","og_type":"article","og_title":"SHAP: interpreting AI models","og_description":"The ability to understand and explain the decisions taken by Artificial Intelligence or Machine Learning models has become essential. These sophisticated","og_url":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models","og_site_name":"Data Science Courses | DataScientest","article_publisher":"https:\/\/www.facebook.com\/DataScientestEN","article_published_time":"2024-05-01T02:26:00+00:00","article_modified_time":"2024-04-01T14:50:13+00:00","og_image":[{"width":768,"height":439,"url":"https:\/\/datascientest.com\/en\/files\/2024\/05\/SHAP_datascientest-768x439-1.jpg","type":"image\/jpeg"}],"author":"Melanie","twitter_card":"summary_large_image","twitter_creator":"@DataScientest__","twitter_site":"@DataScientest__","twitter_misc":{"Written by":"Melanie","Estimated reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models#article","isPartOf":{"@id":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models"},"author":{"name":"Melanie","@id":"https:\/\/datascientest.com\/en\/#\/schema\/person\/19d5f7ade9407eb69af3bf6d1ae1731d"},"headline":"SHAP: interpreting AI models","datePublished":"2024-05-01T02:26:00+00:00","dateModified":"2024-04-01T14:50:13+00:00","mainEntityOfPage":{"@id":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models"},"wordCount":745,"commentCount":0,"publisher":{"@id":"https:\/\/datascientest.com\/en\/#organization"},"articleSection":["Non class\u00e9"],"inLanguage":"en-GB","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/datascientest.com\/en\/shap-interpreting-ai-models#respond"]}],"copyrightYear":"2024","copyrightHolder":{"@id":"https:\/\/datascientest.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models","url":"https:\/\/datascientest.com\/en\/shap-interpreting-ai-models","name":"SHAP: interpreting AI models","isPartOf":{"@id":"https:\/\/datascientest.com\/en\/#website"},"datePublished":"2024-05-01T02:26:00+00:00","dateModified":"2024-04-01T14:50:13+00:00","description":"SHAP (SHapley Additive exPlanations) is a powerful tool for interpreting machine learning models, including but not...","inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/datascientest.com\/en\/shap-interpreting-ai-models"]}]},{"@type":"WebSite","@id":"https:\/\/datascientest.com\/en\/#website","url":"https:\/\/datascientest.com\/en\/","name":"Data Science Courses | DataScientest","description":"Leader in Data Science Courses","publisher":{"@id":"https:\/\/datascientest.com\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/datascientest.com\/en\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/datascientest.com\/en\/#organization","name":"DataScientest","url":"https:\/\/datascientest.com\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/datascientest.com\/en\/#\/schema\/logo\/image\/","url":"https:\/\/datascientest.com\/en\/wp-content\/blogs.dir\/9\/files\/2024\/02\/DataScientest_icon_blue-2.png","contentUrl":"https:\/\/datascientest.com\/en\/wp-content\/blogs.dir\/9\/files\/2024\/02\/DataScientest_icon_blue-2.png","width":301,"height":301,"caption":"DataScientest"},"image":{"@id":"https:\/\/datascientest.com\/en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DataScientestEN","https:\/\/twitter.com\/DataScientest__","https:\/\/www.linkedin.com\/school\/datascientest\/mycompany\/","https:\/\/www.tiktok.com\/@datascientest"]},{"@type":"Person","@id":"https:\/\/datascientest.com\/en\/#\/schema\/person\/19d5f7ade9407eb69af3bf6d1ae1731d","name":"Melanie","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/datascientest.com\/en\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/8d3d660a0698de06f13ecf4823519da1?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/8d3d660a0698de06f13ecf4823519da1?s=96&d=mm&r=g","caption":"Melanie"},"url":"https:\/\/datascientest.com\/en\/author\/melaniekrause"}]}},"_links":{"self":[{"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/posts\/184144"}],"collection":[{"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/users\/67"}],"replies":[{"embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/comments?post=184144"}],"version-history":[{"count":0,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/posts\/184144\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/media\/184147"}],"wp:attachment":[{"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/media?parent=184144"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/categories?post=184144"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/tags?post=184144"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}