{"id":10920,"date":"2020-02-12T06:33:11","date_gmt":"2020-02-12T11:33:11","guid":{"rendered":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=10920"},"modified":"2020-02-12T06:33:11","modified_gmt":"2020-02-12T11:33:11","slug":"open-source-library-provides-explanation-for-machine-learning-through-diverse-counterfactuals","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/open-source-library-provides-explanation-for-machine-learning-through-diverse-counterfactuals\/10920\/","title":{"rendered":"Open-Source Library Provides Explanation for Machine Learning Through Diverse Counterfactuals"},"content":{"rendered":"Originally published in Microsoft Research Blog, January 28, 2020 Consider a person who applies for a loan with a financial company, but their application is rejected by a machine learning algorithm used to determine who receives a loan from the company. How would you explain the decision made by the algorithm to this person? One option is to provide them with a list of features that contributed to the algorithm\u2019s decision, such as income and credit score. Many of the current explanation methods provide this information by either analyzing the algorithm\u2019s properties or approximating it with a simpler, <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/open-source-library-provides-explanation-for-machine-learning-through-diverse-counterfactuals\/10920\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally published in Microsoft Research Blog, January 28, 2020 Consider a person who applies for a loan with a financial company, but their application is rejected by a machine learning algorithm used to determine who receives a loan from the company. How would you explain the decision made by the algorithm to this person? One [&hellip;]<\/p>\n","protected":false},"author":72,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[11,48],"tags":[879,1070,1071,1072,243,8],"class_list":["post-10920","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-ai","tag-analytics-research","tag-artificial-inteligence","tag-counterfactual-explanations","tag-machine-learning","tag-predictive-analytics"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/10920","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/users\/72"}],"replies":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/comments?post=10920"}],"version-history":[{"count":1,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/10920\/revisions"}],"predecessor-version":[{"id":10921,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/10920\/revisions\/10921"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=10920"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=10920"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=10920"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}