{"id":167218,"date":"2023-03-22T11:09:30","date_gmt":"2023-03-22T10:09:30","guid":{"rendered":"https:\/\/datascientest.com\/en\/?p=167218"},"modified":"2023-10-30T18:47:39","modified_gmt":"2023-10-30T17:47:39","slug":"management-of-unbalanced-classification-problems-ii","status":"publish","type":"post","link":"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii","title":{"rendered":"Managing Unbalanced Classification Problems \u2013 Part 2"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"167218\" class=\"elementor elementor-167218\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-14c954f e-flex e-con-boxed e-con\" data-id=\"14c954f\" 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-a5b461e elementor-widget elementor-widget-text-editor\" data-id=\"a5b461e\" 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><strong>This article will be divided into two parts: <a href=\"http:\/\/This article will be divided into two parts: The first focuses on the choice of metrics specific to this type of data, the second details the range of useful methods to obtain a successful model.\" data-wplink-url-error=\"true\">The first focuses on the choice of metrics specific to this type of data<\/a>, the second details the range of useful methods to obtain a successful model.<\/strong><\/p><p><span style=\"font-weight: 400;\">After detailing the<\/span><b> different problems related<\/b><span style=\"font-weight: 400;\"> to data imbalance and demonstrating that the choice of the right performance metric is essential for the evaluation of our models, we will present a non-exhaustive list of useful techniques to fight against this type of problem.<\/span><\/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-f4dfc3d e-flex e-con-boxed e-con\" data-id=\"f4dfc3d\" 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-e7f9a53 elementor-widget elementor-widget-heading\" data-id=\"e7f9a53\" 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><h5 class=\"elementor-heading-title elementor-size-default\">Collect more data\n<\/h5>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4a68c5e elementor-widget elementor-widget-text-editor\" data-id=\"4a68c5e\" 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><span style=\"font-weight: 400;\">This may sound simplistic, but collecting more data is almost always <\/span><b>overlooked<\/b><span style=\"font-weight: 400;\"> and can sometimes be effective.<\/span><\/p><p><span style=\"font-weight: 400;\">Can you collect more data? Take a few minutes to think about collecting more data for your problem, it could potentially rebalance your classes to some degree.<\/span><\/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-2070971 e-flex e-con-boxed e-con\" data-id=\"2070971\" 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-9d915ab elementor-widget elementor-widget-heading\" data-id=\"9d915ab\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h5 class=\"elementor-heading-title elementor-size-default\">Use resampling methods <\/h5>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-95638c5 elementor-widget elementor-widget-text-editor\" data-id=\"95638c5\" 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><span style=\"font-weight: 400;\">You can change the dataset you use before training your <\/span><b>predictive model<\/b><span style=\"font-weight: 400;\"> to have more balanced data.<\/span><\/p><p><span style=\"font-weight: 400;\">This strategy is called resampling and there are two main methods you can use to equalize the classes:\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">Oversampling and Undersampling.\u00a0<\/span><\/p><p><b>Oversampling methods<\/b><span style=\"font-weight: 400;\"> work by increasing the <\/span><b>number of observations<\/b><span style=\"font-weight: 400;\"> of the minority class(es) in order to achieve a satisfactory ratio of minority class to majority class.<\/span><\/p><p><b>Undersampling methods<\/b><span style=\"font-weight: 400;\"> work by decreasing the number of observations of the majority class(es) in order to reach a satisfactory ratio of minority class to majority class.\u00a0<\/span><\/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-601c549 elementor-widget elementor-widget-html\" data-id=\"601c549\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script src=\"https:\/\/gist.github.com\/Raphkas15\/4d8f9f412777b591abb20629f45d4d0a.js\"><\/script>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bbde165 elementor-widget elementor-widget-text-editor\" data-id=\"bbde165\" 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><span style=\"font-weight: 400;\">These approaches are very easy to implement and quick to execute. They are a great starting point.<\/span><\/p><p><span style=\"font-weight: 400;\">Our advice: always <\/span><b>try both approaches<\/b><span style=\"font-weight: 400;\"> on all your unbalanced datasets, and check if it improves your chosen performance metrics.<\/span><\/p><p><b>Favor downsampling when you have large datasets<\/b><span style=\"font-weight: 400;\">: tens or hundreds of thousands of cases or more.<\/span><\/p><p><span style=\"font-weight: 400;\">Consider oversampling when you don&#8217;t have a lot of data: tens of thousands or less.<\/span><\/p><p><span style=\"font-weight: 400;\">Consider testing different class ratios. For example, you don&#8217;t have to aim for a 1:1 ratio in a binary classification problem, try other ratios.<\/span><\/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-2099d30 e-flex e-con-boxed e-con\" data-id=\"2099d30\" 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-adf3f30 elementor-widget elementor-widget-heading\" data-id=\"adf3f30\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h5 class=\"elementor-heading-title elementor-size-default\">Synthetic sample generation\n<\/h5>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-232d835 elementor-widget elementor-widget-text-editor\" data-id=\"232d835\" 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><span style=\"font-weight: 400;\">There are algorithms to generate synthetic samples automatically. The most popular of these algorithms is<\/span><b> SMOTE<\/b><span style=\"font-weight: 400;\"> (for Synthetic Minority Over-sampling Technique). As the name suggests, SMOTE is an oversampling method. It works by <\/span><b>creating synthetic samples<\/b><span style=\"font-weight: 400;\"> from the minority class instead of creating simple copies.\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">To learn more about SMOTE, see <\/span><strong><a href=\"https:\/\/arxiv.org\/pdf\/1106.1813.pdf\">the original article<\/a><\/strong><span style=\"font-weight: 400;\">.<\/span><\/p><p><span style=\"font-weight: 400;\">The<\/span><b> ClusterCentroids algorithm<\/b><span style=\"font-weight: 400;\"> is an Undersampling algorithm that uses Clustering methods to generate a number of centroids from the original data, in order to lose as little information as possible about the majority class, when it needs to be reduced.<\/span><\/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-9af778c elementor-widget elementor-widget-html\" data-id=\"9af778c\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script src=\"https:\/\/gist.github.com\/Raphkas15\/910ed14bd6e2e5ec83502f00d3000075.js\"><\/script>\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-bff48f0 e-flex e-con-boxed e-con\" data-id=\"bff48f0\" 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-49e4029 elementor-widget elementor-widget-heading\" data-id=\"49e4029\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h5 class=\"elementor-heading-title elementor-size-default\">Rethink the problem, find an other way to solvre the problem<\/h5>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1dd693d elementor-widget elementor-widget-text-editor\" data-id=\"1dd693d\" 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><span style=\"font-weight: 400;\">Sometimes resampling methods are <\/span><b>not efficient enough<\/b><span style=\"font-weight: 400;\">, and in this case, it is necessary to rethink the problem. It may be that the algorithm used is not suitable for your data.\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">Do not hesitate to test other algorithms, possibly combined with the resampling methods seen above.<\/span><\/p><p><b>Tree-based ensemble models<\/b><span style=\"font-weight: 400;\"> such as RandomForest are generally more suitable for unbalanced data.<\/span><\/p><p><span style=\"font-weight: 400;\">It is also possible to <\/span><b>play with the probabilities<\/b><span style=\"font-weight: 400;\">. For example, if we want to be able to predict the vast majority of potential churners, even if it means misclassifying some <\/span><b>non-churners<\/b><span style=\"font-weight: 400;\">, we can modify the probability threshold above which customers are considered as churners.<\/span><\/p><p><span style=\"font-weight: 400;\">The lower the threshold, the higher the precision of our class, but the recall will decrease.<\/span><\/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-9ef2da9 elementor-widget elementor-widget-html\" data-id=\"9ef2da9\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script src=\"https:\/\/gist.github.com\/Raphkas15\/982e8e5d95945fe57aea303357ba9f74.js\"><\/script>\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-15822d9 e-flex e-con-boxed e-con\" data-id=\"15822d9\" 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-dc686f0 elementor-widget elementor-widget-heading\" data-id=\"dc686f0\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h5 class=\"elementor-heading-title elementor-size-default\">Use a penalized model<\/h5>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-50f2333 elementor-widget elementor-widget-text-editor\" data-id=\"50f2333\" 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><span style=\"font-weight: 400;\">Penalized classification <\/span><b>imposes an additional cost<\/b><span style=\"font-weight: 400;\"> on the model for classification errors made on the minority class during training. These penalties can bias the model to pay more attention to the minority class.<\/span><\/p><p><span style=\"font-weight: 400;\">In most classes of <\/span><b>scikit-learn algorithms<\/b><span style=\"font-weight: 400;\">, it is possible to simply use the `class_weight` parameter. It allows penalizing errors made on a class by a new weight.\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">The higher the weight of a class, the more errors in this class are penalized, and the more importance is given to it.<\/span><\/p><p><span style=\"font-weight: 400;\">The weights should be given in dictionary form, e.g. `{0:1, 1:5}`, to give 5 times the weight to errors made on class 1.\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">The argument `&#8221;balanced&#8221;` allows us to associate with each class a weight inversely proportional to its frequency.<\/span><\/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-32ec297 elementor-widget elementor-widget-html\" data-id=\"32ec297\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script src=\"https:\/\/gist.github.com\/Raphkas15\/84db253c0e288f5622750d397f74af49.js\"><\/script>\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-398aa59 e-flex e-con-boxed e-con\" data-id=\"398aa59\" 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-56c1975 elementor-widget elementor-widget-heading\" data-id=\"56c1975\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h5 class=\"elementor-heading-title elementor-size-default\">Use methods generating subsampled subsets<\/h5>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-78c6522 elementor-widget elementor-widget-text-editor\" data-id=\"78c6522\" 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><span style=\"font-weight: 400;\">Another solution proposed by the <\/span><b>imblearn.ensemble<\/b><span style=\"font-weight: 400;\"> module, is the use of classes containing ensemble models such as<\/span><b> Boosting or Bagging<\/b><span style=\"font-weight: 400;\"> which are trained at each step of the algorithm on a sample automatically rebalanced between the different classes.<\/span><\/p><p><span style=\"font-weight: 400;\">These model implementations make it possible to dispense with <\/span><b>resampling methods<\/b><span style=\"font-weight: 400;\"> before training and to apply them automatically to each selection of data by the algorithm.<\/span><\/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-4279bf3 e-flex e-con-boxed e-con\" data-id=\"4279bf3\" 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-318b215 elementor-widget elementor-widget-heading\" data-id=\"318b215\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h5 class=\"elementor-heading-title elementor-size-default\">Think out of the box, be creative <\/h5>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-845f0be elementor-widget elementor-widget-text-editor\" data-id=\"845f0be\" 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><span style=\"font-weight: 400;\">You can test all of these techniques, combine them, or even think about <\/span><b>relabeling the majority class data<\/b><span style=\"font-weight: 400;\"> into subclasses to get a more balanced multi-class classification problem.<\/span><\/p><p><span style=\"font-weight: 400;\">In some cases, you can also think about using other <\/span><a href=\"https:\/\/datascientest.com\/en\/machine-learning-what-is-it-and-why-does-it-change-the-world\"><b>Machine Learning methods<\/b><\/a><span style=\"font-weight: 400;\"> like Anomaly Detection or Active Learning.<\/span><\/p><p><span style=\"font-weight: 400;\">We have presented many techniques, which you can choose from when working with this kind of data. Feel free to test these methods individually, and start with the simplest ones!<\/span><\/p><p><span style=\"font-weight: 400;\">Want to improve your skills in building powerful and reliable models from unbalanced data sets?<\/span><\/p><p><span style=\"font-weight: 400;\">Don&#8217;t hesitate to <\/span><a href=\"https:\/\/datascientest.com\/en\/appointment\"><b>contact us<\/b><\/a><span style=\"font-weight: 400;\"> for more information!<\/span><\/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-741c4d8 elementor-widget elementor-widget-html\" data-id=\"741c4d8\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<script src=\"https:\/\/gist.github.com\/Raphkas15\/84db253c0e288f5622750d397f74af49.js\"><\/script>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2614a2e elementor-align-center button-principal elementor-widget elementor-widget-button\" data-id=\"2614a2e\" 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-md\" href=\"https:\/\/datascientest.com\/en\/data-courses\">\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\">Start a Training in Data Science <\/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-a587604 e-flex e-con-boxed e-con\" data-id=\"a587604\" 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\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>This article will be divided into two parts: The first focuses on the choice of metrics specific to this type of data, the second details the range of useful methods to obtain a successful model. After detailing the different problems related to data imbalance and demonstrating that the choice of the right performance metric is [&hellip;]<\/p>\n","protected":false},"author":63,"featured_media":167193,"comment_status":"open","ping_status":"open","sticky":false,"template":"elementor_theme","format":"standard","meta":{"content-type":"","inline_featured_image":false},"categories":[2425],"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>Managing Unbalanced Classification Problems \u2013 Part 2<\/title>\n<meta name=\"description\" content=\"After detailing the different problems related to data imbalance and demonstrating that the choice of the right performance metric is essential for the evaluation of our models, we will present a non-exhaustive list of useful techniques to fight against this type of problem.\" \/>\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\/management-of-unbalanced-classification-problems-ii\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Managing Unbalanced Classification Problems \u2013 Part 2\" \/>\n<meta property=\"og:description\" content=\"This article will be divided into two parts: The first focuses on the choice of metrics specific to this type of data, the second details the range of\" \/>\n<meta property=\"og:url\" content=\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii\" \/>\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=\"2023-03-22T10:09:30+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-30T17:47:39+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/datascientest.com\/en\/files\/2023\/03\/desequilibre_cost_sensitive_learning.png\" \/>\n\t<meta property=\"og:image:width\" content=\"614\" \/>\n\t<meta property=\"og:image:height\" content=\"466\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\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=\"\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii#article\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii\"},\"author\":{\"name\":\"\",\"@id\":\"\"},\"headline\":\"Managing Unbalanced Classification Problems \u2013 Part 2\",\"datePublished\":\"2023-03-22T10:09:30+00:00\",\"dateModified\":\"2023-10-30T17:47:39+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii\"},\"wordCount\":859,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/datascientest.com\/en\/#organization\"},\"articleSection\":[\"Data Science\"],\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii#respond\"]}],\"copyrightYear\":\"2023\",\"copyrightHolder\":{\"@id\":\"https:\/\/datascientest.com\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii\",\"url\":\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii\",\"name\":\"Managing Unbalanced Classification Problems \u2013 Part 2\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/en\/#website\"},\"datePublished\":\"2023-03-22T10:09:30+00:00\",\"dateModified\":\"2023-10-30T17:47:39+00:00\",\"description\":\"After detailing the different problems related to data imbalance and demonstrating that the choice of the right performance metric is essential for the evaluation of our models, we will present a non-exhaustive list of useful techniques to fight against this type of problem.\",\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii\"]}]},{\"@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\":\"\",\"url\":\"https:\/\/datascientest.com\/en\/author\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Managing Unbalanced Classification Problems \u2013 Part 2","description":"After detailing the different problems related to data imbalance and demonstrating that the choice of the right performance metric is essential for the evaluation of our models, we will present a non-exhaustive list of useful techniques to fight against this type of problem.","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\/management-of-unbalanced-classification-problems-ii","og_locale":"en_GB","og_type":"article","og_title":"Managing Unbalanced Classification Problems \u2013 Part 2","og_description":"This article will be divided into two parts: The first focuses on the choice of metrics specific to this type of data, the second details the range of","og_url":"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii","og_site_name":"Data Science Courses | DataScientest","article_publisher":"https:\/\/www.facebook.com\/DataScientestEN","article_published_time":"2023-03-22T10:09:30+00:00","article_modified_time":"2023-10-30T17:47:39+00:00","og_image":[{"width":614,"height":466,"url":"https:\/\/datascientest.com\/en\/files\/2023\/03\/desequilibre_cost_sensitive_learning.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_creator":"@DataScientest__","twitter_site":"@DataScientest__","twitter_misc":{"Written by":"","Estimated reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii#article","isPartOf":{"@id":"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii"},"author":{"name":"","@id":""},"headline":"Managing Unbalanced Classification Problems \u2013 Part 2","datePublished":"2023-03-22T10:09:30+00:00","dateModified":"2023-10-30T17:47:39+00:00","mainEntityOfPage":{"@id":"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii"},"wordCount":859,"commentCount":0,"publisher":{"@id":"https:\/\/datascientest.com\/en\/#organization"},"articleSection":["Data Science"],"inLanguage":"en-GB","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii#respond"]}],"copyrightYear":"2023","copyrightHolder":{"@id":"https:\/\/datascientest.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii","url":"https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii","name":"Managing Unbalanced Classification Problems \u2013 Part 2","isPartOf":{"@id":"https:\/\/datascientest.com\/en\/#website"},"datePublished":"2023-03-22T10:09:30+00:00","dateModified":"2023-10-30T17:47:39+00:00","description":"After detailing the different problems related to data imbalance and demonstrating that the choice of the right performance metric is essential for the evaluation of our models, we will present a non-exhaustive list of useful techniques to fight against this type of problem.","inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/datascientest.com\/en\/management-of-unbalanced-classification-problems-ii"]}]},{"@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":"","url":"https:\/\/datascientest.com\/en\/author"}]}},"_links":{"self":[{"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/posts\/167218"}],"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\/63"}],"replies":[{"embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/comments?post=167218"}],"version-history":[{"count":0,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/posts\/167218\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/media\/167193"}],"wp:attachment":[{"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/media?parent=167218"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/categories?post=167218"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascientest.com\/en\/wp-json\/wp\/v2\/tags?post=167218"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}