{"id":9620,"date":"2025-07-10T10:44:21","date_gmt":"2025-07-10T08:44:21","guid":{"rendered":"https:\/\/www.kubicek.ai\/?post_type=lexicon&#038;p=9620"},"modified":"2026-07-28T09:58:43","modified_gmt":"2026-07-28T07:58:43","slug":"classification","status":"publish","type":"lexicon","link":"https:\/\/www.kubicek.ai\/en\/lexicon\/classification\/","title":{"rendered":"Classification"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\"><strong>Classification<\/strong>, in machine learning, is the process of assigning input data to predefined categories or classes. The aim is to teach a model to recognise patterns in data and, on that basis, correctly assign new, unknown data to one of those classes.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">How classification works<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The basis for classification is training data in which every data point is marked with the correct category (a &#8220;label&#8221;). From these examples the model learns which properties (features) are typical of the individual classes. Think of it as learning to recognise fruit. You show the model thousands of pictures labelled &#8220;apple&#8221;, &#8220;banana&#8221; or &#8220;orange&#8221;. The model learns that a red round thing is probably an apple, while a yellow elongated one is a banana. Once trained, it should be able to classify correctly even a picture of fruit it has never seen before.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Types of classification task<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Classification problems divide into several basic types according to the nature of the categories:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Binary classification<\/strong>: the task has only two possible categories. This is the simplest form of classification. Example: deciding whether an e-mail is spam or not spam.<\/li>\n\n\n\n<li><strong>Multi-class classification<\/strong>: there are more than two categories, but each data point can be assigned exactly one of them. Example: recognising handwritten digits from 0 to 9. Each image of a digit can be only one of ten options.<\/li>\n\n\n\n<li><strong>Multi-label classification<\/strong>: there are several categories and one data point may be assigned several labels at once. Example: analysing film genre, where one film can be action, comedy and science fiction simultaneously.<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">The process of building a classification model<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Creating a working classification model usually involves the following steps:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Collecting and preparing data<\/strong>: obtaining a sufficient quantity of labelled data and cleaning it.<\/li>\n\n\n\n<li><strong>Splitting the data<\/strong>: the data are typically divided into a training set (for learning the model), a validation set (for tuning parameters) and a test set (for final performance assessment).<\/li>\n\n\n\n<li><strong>Choosing a model<\/strong>: selecting a suitable classification algorithm according to the nature of the data and the task.<\/li>\n\n\n\n<li><strong>Training the model<\/strong>: &#8220;teaching&#8221; the model on the training data.<\/li>\n\n\n\n<li><strong>Evaluation<\/strong>: measuring the model&#8217;s success on the test data using metrics such as accuracy, recall or the F1 score.<\/li>\n\n\n\n<li><strong>Deployment<\/strong>: if the model is successful enough, it is put into practice to classify new data.<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Common classification algorithms<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">There are many algorithms that can be used for classification. Among the best known are:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong><a href=\"https:\/\/www.kubicek.ai\/en\/lexicon\/logistic-regression\/\" class=\"lex-link\">Logistic regression<\/a><\/strong>: a simple, fast model often used for binary classification.<\/li>\n\n\n\n<li><strong>k-Nearest Neighbors (k-NN)<\/strong>: classifies a new point on the basis of a majority vote of its &#8220;neighbours&#8221; in the data.<\/li>\n\n\n\n<li><strong>Decision trees and random forests<\/strong>: build a flowchart-like structure for making decisions. A random forest combines several trees for more robust results.<\/li>\n\n\n\n<li><strong>Support vector machines (SVM)<\/strong>: search for the optimal boundary (hyperplane) between the individual classes.<\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.kubicek.ai\/en\/lexicon\/neural-networks\/\" class=\"lex-link\">Neural networks<\/a><\/strong>: complex models inspired by the human brain, very effective for demanding tasks such as image recognition or natural language processing.<\/li>\n<\/ul>\n","protected":false},"featured_media":0,"template":"","class_list":["post-9620","lexicon","type-lexicon","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/lexicon\/9620","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/lexicon"}],"about":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/types\/lexicon"}],"wp:attachment":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/media?parent=9620"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}