{"id":5920,"date":"2025-08-20T10:47:32","date_gmt":"2025-08-20T10:47:32","guid":{"rendered":"https:\/\/detralytics.com\/?p=5920"},"modified":"2025-09-10T11:57:46","modified_gmt":"2025-09-10T11:57:46","slug":"insurance-analytics-actuarial-neural-networks-module-3","status":"publish","type":"post","link":"https:\/\/detralytics.com\/fr\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/","title":{"rendered":"Sciences des donn\u00e9es et modelling assurantiel | Module 3 : R\u00e9seaux de neurones"},"content":{"rendered":"<div data-elementor-type=\"wp-post\" data-elementor-id=\"5920\" class=\"elementor elementor-5920\" data-elementor-post-type=\"post\">\n\t\t\t\t<div class=\"elementor-element elementor-element-509421b e-con-full e-flex e-con e-parent\" data-id=\"509421b\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;,&quot;shape_divider_bottom&quot;:&quot;tilt&quot;}\">\n\t\t\t\t<div class=\"elementor-shape elementor-shape-bottom\" aria-hidden=\"true\" data-negative=\"false\">\n\t\t\t<svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" viewbox=\"0 0 1000 100\" preserveaspectratio=\"none\">\n\t<path class=\"elementor-shape-fill\" d=\"M0,6V0h1000v100L0,6z\"\/>\n<\/svg>\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3243311 elementor-widget elementor-widget-heading\" data-id=\"3243311\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h1 class=\"elementor-heading-title elementor-size-default\">Sciences des donn\u00e9es et modelling assurantiel | Module 3 : R\u00e9seaux de neurones<\/h1>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-41f20e4 elementor-widget elementor-widget-heading\" data-id=\"41f20e4\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">D. Hainaut, PhD<\/h3>\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-4fae3a2 e-con-full e-flex e-con e-parent\" data-id=\"4fae3a2\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t<div class=\"elementor-element elementor-element-ab7afb1 e-con-full e-flex e-con e-child\" data-id=\"ab7afb1\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-254f0bc elementor-widget elementor-widget-heading\" data-id=\"254f0bc\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Description<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d2e84fd elementor-widget elementor-widget-text-editor\" data-id=\"d2e84fd\" data-element_type=\"widget\" data-e-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\t\t<div class=\"page\" title=\"Page 3\">\n<div class=\"layoutArea\">\n<div class=\"column\">\n<p>Cette formation pr\u00e9sente la th\u00e9orie des r\u00e9seaux de neurones ainsi que de leur application \u00e0 la tarification actuarielle. Elle met l\u2019accent sur l\u2019impl\u00e9mentation pratique en R de ces mod\u00e8les \u00e0 l\u2019aide des librairies Keras et NeuralNet.\u00a0<\/p>\n<p>La formation s\u2019adresse tant aux non-initi\u00e9s qu\u2019aux actuaires ayant des bases en machine learning. Les concepts sont pr\u00e9sent\u00e9s \u00e0 l\u2019aide d\u2019exemples d\u00e9taill\u00e9es pas \u00e0 pas. La formation d\u00e9bute par une pr\u00e9sentation des perceptrons multicouches ainsi que leur calibration. Nous montrons ensuite comment un perceptron permet de r\u00e9duire la dimension d\u2019un jeu de donn\u00e9es et nous terminons par une pr\u00e9sentation du neural gradient boosting. Le code R des illustrations est fourni aux participants.\u00a0<\/p>\n<\/div>\n<\/div>\n<\/div>\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-79a6580 elementor-widget elementor-widget-heading\" data-id=\"79a6580\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Programme<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d821de4 elementor-widget elementor-widget-text-editor\" data-id=\"d821de4\" data-element_type=\"widget\" data-e-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\t\t<p>Nous commen\u00e7ons ce cours par une r\u00e9vision des concepts \u00e0 la base des r\u00e9seaux de neurones et des m\u00e9thodes de calibration. Une \u00e9tude de cas (base de donn\u00e9es Wasa) illustre l\u2019utilisation des r\u00e9seaux de neurones pour la tarification en assurance non-vie.<\/p>\n<p>Nous poursuivons avec une introduction \u00e0 NeuralNet et Keras, au cours de laquelle les participants pourront tester le code R utilis\u00e9 dans les illustrations. Nous verrons \u00e9galement comment lutter contre le surapprentissage gr\u00e2ce aux approches Dropout, Lasso et Ridge.<\/p>\n<p>Enfin, nous montrons comment les r\u00e9seaux de neurones \u00e0 goulot d\u2019\u00e9tranglement peuvent \u00eatre utilis\u00e9s pour r\u00e9duire la dimension d\u2019un jeu de donn\u00e9es, de mani\u00e8re analogue \u00e0 une analyse en composantes principales non lin\u00e9aire. Cette technique sera illustr\u00e9e sur la pr\u00e9vision de la mortalit\u00e9. Le code R sera mis \u00e0 disposition des participants.<\/p>\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-7daa359 e-con-full e-flex e-con e-child\" data-id=\"7daa359\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-355647c elementor-widget elementor-widget-heading\" data-id=\"355647c\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Orateur<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2a56262 elementor-widget elementor-widget-image\" data-id=\"2a56262\" data-element_type=\"widget\" data-e-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 fetchpriority=\"high\" decoding=\"async\" width=\"1042\" height=\"1042\" src=\"https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond.jpg\" class=\"attachment-full size-full wp-image-2876\" alt=\"Donatien Hainaut\" srcset=\"https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond.jpg 1042w, https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond-768x768.jpg 768w, https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond-146x146.jpg 146w, https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond-50x50.jpg 50w, https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond-75x75.jpg 75w, https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond-85x85.jpg 85w, https:\/\/detralytics.com\/wp-content\/uploads\/2023\/07\/Donatien_Rond-80x80.jpg 80w\" sizes=\"(max-width: 1042px) 100vw, 1042px\" \/>\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 class=\"elementor-element elementor-element-ab825d4 elementor-widget elementor-widget-heading\" data-id=\"ab825d4\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Donatien Hainaut<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d353b87 elementor-widget elementor-widget-text-editor\" data-id=\"d353b87\" data-element_type=\"widget\" data-e-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\t\t<p><em>Conseiller Scientifique, Detralytics<\/em><br \/><em>Professeur, UCLouvain<\/em><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-0f29719 e-con-full e-flex e-con e-child\" data-id=\"0f29719\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;gradient&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-5de7e2a elementor-widget elementor-widget-text-editor\" data-id=\"5de7e2a\" data-element_type=\"widget\" data-e-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\t\t<p><b>Date : <\/b>\u00c0 la demande<\/p>\n<p><b><\/b><b>Dur\u00e9e : <\/b>9h<\/p>\n<p><b style=\"letter-spacing: 0.3px; background-color: transparent;\">Accr\u00e9ditation :<\/b><span style=\"letter-spacing: 0.3px; background-color: transparent;\"> 9CPD | 54PPC<\/span><\/p>\n<p><b>Pr\u00e9requis :<\/b> Installation de packages R<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-678e6db e-con-full e-flex e-con e-child\" data-id=\"678e6db\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-898935e elementor-align-center elementor-widget elementor-widget-button\" data-id=\"898935e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"mailto:learning@detralytics.eu\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Introduire une demande<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\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-89b6347 e-con-full e-flex e-con e-parent\" data-id=\"89b6347\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-383049d elementor-widget elementor-widget-heading\" data-id=\"383049d\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Comp\u00e9tences acquises<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bc0d89b elementor-widget elementor-widget-text-editor\" data-id=\"bc0d89b\" data-element_type=\"widget\" data-e-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\t\t<p><strong><u>Concepts:<\/u><\/strong><\/p>\n<ul>\n<li>Introduction aux r\u00e9seaux de neurones feed-forward<\/li>\n<li>R\u00e9seaux de neurones avec gradient boosting<\/li>\n<li>Entra\u00eenement de r\u00e9seaux supervis\u00e9s<\/li>\n<li>Application \u00e0 la tarification en assurance non-vie<\/li>\n<li>\u00c9tude de cas : base de donn\u00e9es Wasa<\/li>\n<\/ul>\n<p>\u00a0<\/p>\n<p><strong><u>Mise en pratique :<\/u><\/strong><\/p>\n<ul>\n<li>Impl\u00e9mentation : Excel, NeuralNet et Keras<\/li>\n<li>Validation crois\u00e9e<\/li>\n<li>Lutte contre le surapprentissage : Lasso &amp; Ridge<\/li>\n<li>R\u00e9seau \u00e0 goulot d\u2019\u00e9tranglement : une application \u00e0 la pr\u00e9vision de la mortalit\u00e9<\/li>\n<\/ul>\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-6d47b7c e-con-full e-flex e-con e-parent\" data-id=\"6d47b7c\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-cc3d72a elementor-widget elementor-widget-heading\" data-id=\"cc3d72a\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">\u00c0 propos de notre orateur<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-224cb75 elementor-widget elementor-widget-heading\" data-id=\"224cb75\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Donatien Hainaut<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-58dff6d elementor-widget elementor-widget-text-editor\" data-id=\"58dff6d\" data-element_type=\"widget\" data-e-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\t\t<p class=\"has-text-color has-link-color wp-elements-ae5c48d82f22f2e0c01ebb851eee595b\">Donatien Hainaut est Conseiller Scientifique chez Detralytics et Professeur \u00e0 l\u2019UCLouvain (Belgique), o\u00f9 il dirige le Master en Data Science \u00e0 orientation statistique. Auparavant, il a occup\u00e9 plusieurs postes acad\u00e9miques, notamment en tant que Professeur Associ\u00e9 \u00e0 la Rennes School of Business et \u00e0 l\u2019ENSAE \u00e0 Paris. Il poss\u00e8de \u00e9galement une solide exp\u00e9rience en entreprise, ayant travaill\u00e9 comme Risk Officer, Quantitative Analyst et ALM Officer.<\/p><p class=\"has-text-color has-link-color wp-elements-319687f5e483df5041193c0b748e25dd\">Actuaire qualifi\u00e9 et titulaire d\u2019un doctorat en Asset and Liability Management, ses recherches actuelles portent sur les m\u00e9canismes de contagion dans les processus stochastiques ainsi que sur les applications des r\u00e9seaux de neurones en assurance.<\/p>\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-ead9557 e-flex e-con-boxed e-con e-parent\" data-id=\"ead9557\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-20d4992 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"20d4992\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/detralytics.com\/fr\/trainings\/#opentrainings\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-icon\">\n\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-arrow-right\" viewbox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M190.5 66.9l22.2-22.2c9.4-9.4 24.6-9.4 33.9 0L441 239c9.4 9.4 9.4 24.6 0 33.9L246.6 467.3c-9.4 9.4-24.6 9.4-33.9 0l-22.2-22.2c-9.5-9.5-9.3-25 .4-34.3L311.4 296H24c-13.3 0-24-10.7-24-24v-32c0-13.3 10.7-24 24-24h287.4L190.9 101.2c-9.8-9.3-10-24.8-.4-34.3z\"><\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Nos formations<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\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\t\t<\/div>","protected":false},"excerpt":{"rendered":"<p>Cette formation pr\u00e9sente la th\u00e9orie des r\u00e9seaux de neurones ainsi que de leur application \u00e0 la tarification actuarielle. Elle met l\u2019accent sur l\u2019impl\u00e9mentation pratique en R.<\/p>","protected":false},"author":1,"featured_media":5741,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[153],"tags":[149],"class_list":["post-5920","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-science","tag-data-science"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.9 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Training : Interpretability of Machine Learning models in Python<\/title>\n<meta name=\"description\" content=\"The aim of this course is to introduce the local and global methods analyzing relations between output and input of complex ML algorithms.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/detralytics.com\/fr\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Training : Interpretability of Machine Learning models in Python\" \/>\n<meta property=\"og:description\" content=\"The aim of this course is to introduce the local and global methods analyzing relations between output and input of complex ML algorithms.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/detralytics.com\/fr\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/\" \/>\n<meta property=\"og:site_name\" content=\"detralytics.com\" \/>\n<meta property=\"article:published_time\" content=\"2025-08-20T10:47:32+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-10T11:57:46+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/detralytics.com\/wp-content\/uploads\/2025\/08\/insurance-vert-scaled.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2560\" \/>\n\t<meta property=\"og:image:height\" content=\"1535\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Detralytics\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Detralytics\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/\"},\"author\":{\"name\":\"Detralytics\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/#\\\/schema\\\/person\\\/afceedbd1f9efae3aff3db243bb1890d\"},\"headline\":\"Insurance analytics | Module 3 : Actuarial neural networks\",\"datePublished\":\"2025-08-20T10:47:32+00:00\",\"dateModified\":\"2025-09-10T11:57:46+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/\"},\"wordCount\":341,\"publisher\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/detralytics.com\\\/wp-content\\\/uploads\\\/2025\\\/08\\\/insurance-vert-scaled.jpg\",\"keywords\":[\"Data Science\"],\"articleSection\":[\"Data Science\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/\",\"url\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/\",\"name\":\"Training : Interpretability of Machine Learning models in Python\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/detralytics.com\\\/wp-content\\\/uploads\\\/2025\\\/08\\\/insurance-vert-scaled.jpg\",\"datePublished\":\"2025-08-20T10:47:32+00:00\",\"dateModified\":\"2025-09-10T11:57:46+00:00\",\"description\":\"The aim of this course is to introduce the local and global methods analyzing relations between output and input of complex ML algorithms.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/#primaryimage\",\"url\":\"https:\\\/\\\/detralytics.com\\\/wp-content\\\/uploads\\\/2025\\\/08\\\/insurance-vert-scaled.jpg\",\"contentUrl\":\"https:\\\/\\\/detralytics.com\\\/wp-content\\\/uploads\\\/2025\\\/08\\\/insurance-vert-scaled.jpg\",\"width\":2560,\"height\":1535,\"caption\":\"Insurance Analytics\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/learning\\\/data-science\\\/insurance-analytics-actuarial-neural-networks-module-3\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/detralytics.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Insurance analytics | Module 3 : Actuarial neural networks\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/#website\",\"url\":\"https:\\\/\\\/detralytics.com\\\/\",\"name\":\"detralytics.com\",\"description\":\"People Drive Actuarial Innovation\",\"publisher\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/detralytics.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/#organization\",\"name\":\"Detralytics\",\"url\":\"https:\\\/\\\/detralytics.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/detralytics.com\\\/wp-content\\\/uploads\\\/2020\\\/04\\\/NEW-logo-detra.png\",\"contentUrl\":\"https:\\\/\\\/detralytics.com\\\/wp-content\\\/uploads\\\/2020\\\/04\\\/NEW-logo-detra.png\",\"width\":9329,\"height\":2348,\"caption\":\"Detralytics\"},\"image\":{\"@id\":\"https:\\\/\\\/detralytics.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/company\\\/18195267\\\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/detralytics.com\\\/#\\\/schema\\\/person\\\/afceedbd1f9efae3aff3db243bb1890d\",\"name\":\"Detralytics\",\"url\":\"https:\\\/\\\/detralytics.com\\\/fr\\\/author\\\/admin\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Training : Interpretability of Machine Learning models in Python","description":"La formation  d\u00e9bute par une pr\u00e9sentation des outils d\u2019analyse globales tels que les graphes de d\u00e9pendance, les permutations et les interactions. Nous encha\u00eenons ensuite avec les m\u00e9thodes locales par mod\u00e8le agnostique et concluons avec l\u2019approche de Shapley, bas\u00e9e sur la th\u00e9orie des jeux. Le module peut \u00eatre illustr\u00e9 soit en R (IML) ou en Python (Scikit learn). L\u2019ensemble des codes \u00e9tant fournis aux participants.","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:\/\/detralytics.com\/fr\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/","og_locale":"fr_FR","og_type":"article","og_title":"Training : Interpretability of Machine Learning models in Python","og_description":"The aim of this course is to introduce the local and global methods analyzing relations between output and input of complex ML algorithms.","og_url":"https:\/\/detralytics.com\/fr\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/","og_site_name":"detralytics.com","article_published_time":"2025-08-20T10:47:32+00:00","article_modified_time":"2025-09-10T11:57:46+00:00","og_image":[{"width":2560,"height":1535,"url":"https:\/\/detralytics.com\/wp-content\/uploads\/2025\/08\/insurance-vert-scaled.jpg","type":"image\/jpeg"}],"author":"Detralytics","twitter_card":"summary_large_image","twitter_misc":{"\u00c9crit par":"Detralytics","Dur\u00e9e de lecture estim\u00e9e":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/#article","isPartOf":{"@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/"},"author":{"name":"Detralytics","@id":"https:\/\/detralytics.com\/#\/schema\/person\/afceedbd1f9efae3aff3db243bb1890d"},"headline":"Insurance analytics | Module 3 : Actuarial neural networks","datePublished":"2025-08-20T10:47:32+00:00","dateModified":"2025-09-10T11:57:46+00:00","mainEntityOfPage":{"@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/"},"wordCount":341,"publisher":{"@id":"https:\/\/detralytics.com\/#organization"},"image":{"@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/#primaryimage"},"thumbnailUrl":"https:\/\/detralytics.com\/wp-content\/uploads\/2025\/08\/insurance-vert-scaled.jpg","keywords":["Data Science"],"articleSection":["Data Science"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/","url":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/","name":"Training : Interpretability of Machine Learning models in Python","isPartOf":{"@id":"https:\/\/detralytics.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/#primaryimage"},"image":{"@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/#primaryimage"},"thumbnailUrl":"https:\/\/detralytics.com\/wp-content\/uploads\/2025\/08\/insurance-vert-scaled.jpg","datePublished":"2025-08-20T10:47:32+00:00","dateModified":"2025-09-10T11:57:46+00:00","description":"La formation  d\u00e9bute par une pr\u00e9sentation des outils d\u2019analyse globales tels que les graphes de d\u00e9pendance, les permutations et les interactions. Nous encha\u00eenons ensuite avec les m\u00e9thodes locales par mod\u00e8le agnostique et concluons avec l\u2019approche de Shapley, bas\u00e9e sur la th\u00e9orie des jeux. Le module peut \u00eatre illustr\u00e9 soit en R (IML) ou en Python (Scikit learn). L\u2019ensemble des codes \u00e9tant fournis aux participants.","breadcrumb":{"@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/#primaryimage","url":"https:\/\/detralytics.com\/wp-content\/uploads\/2025\/08\/insurance-vert-scaled.jpg","contentUrl":"https:\/\/detralytics.com\/wp-content\/uploads\/2025\/08\/insurance-vert-scaled.jpg","width":2560,"height":1535,"caption":"Insurance Analytics"},{"@type":"BreadcrumbList","@id":"https:\/\/detralytics.com\/learning\/data-science\/insurance-analytics-actuarial-neural-networks-module-3\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/detralytics.com\/"},{"@type":"ListItem","position":2,"name":"Insurance analytics | Module 3 : Actuarial neural networks"}]},{"@type":"WebSite","@id":"https:\/\/detralytics.com\/#website","url":"https:\/\/detralytics.com\/","name":"detralytics.com","description":"People Drive Actuarial Innovation","publisher":{"@id":"https:\/\/detralytics.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/detralytics.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/detralytics.com\/#organization","name":"Detralytics","url":"https:\/\/detralytics.com\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/detralytics.com\/#\/schema\/logo\/image\/","url":"https:\/\/detralytics.com\/wp-content\/uploads\/2020\/04\/NEW-logo-detra.png","contentUrl":"https:\/\/detralytics.com\/wp-content\/uploads\/2020\/04\/NEW-logo-detra.png","width":9329,"height":2348,"caption":"Detralytics"},"image":{"@id":"https:\/\/detralytics.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/company\/18195267\/"]},{"@type":"Person","@id":"https:\/\/detralytics.com\/#\/schema\/person\/afceedbd1f9efae3aff3db243bb1890d","name":"Detralytics","url":"https:\/\/detralytics.com\/fr\/author\/admin\/"}]}},"_links":{"self":[{"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/posts\/5920","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/comments?post=5920"}],"version-history":[{"count":0,"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/posts\/5920\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/media\/5741"}],"wp:attachment":[{"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/media?parent=5920"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/categories?post=5920"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/detralytics.com\/fr\/wp-json\/wp\/v2\/tags?post=5920"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}