Classification

<h2 id="binary-vs-multi-class-classification">Binary vs multi-class classification</h2>
<p>Methodological work aimed at improving the accuracy of a classifier is commonly divided between cases where there are exactly two classes (<a href="/facts/Binary_classification/MeYYAMwp">binary classification</a>) and cases where there are three or more classes (<a href="/facts/Multiclass_classification/aS7sV9EX">multiclass classification</a>).
</p>
<h2 id="evaluation-of-accuracy">Evaluation of accuracy</h2>
<p>Unlike in <a href="/facts/Decision_theory/TbXcQX0v">decision theory</a>, it is assumed that a classifier repeats the classification task over and over. And unlike a <a href="/facts/Lottery/mYwYk5ec">lottery</a>, it is assumed that each classification can be either right or wrong; in the theory of measurement, classification is understood as measurement against a <a href="/facts/Level_of_measurement/8GAxPxFv">nominal</a> scale. Thus it is possible to try to measure the accuracy of a classifier.
</p><p>Measuring the accuracy of a classifier allows a choice to be made between two alternative classifiers. This is important both when developing a classifier and in choosing which classifier to deploy. There are however many different methods for evaluating the accuracy of a classifier and no general method for determining which method should be used in which circumstances. Different fields have taken different approaches, even in binary classification. In <a href="/facts/Pattern_recognition/o1s38opj">pattern recognition</a>, error rate is popular. The <a href="/facts/Gini_coefficient/HledImpA">Gini coefficient</a> and KS statistic are widely used in the credit scoring industry. <a href="/facts/Sensitivity_and_specificity/pzc9qfdz">Sensitivity and specificity</a> are widely used in epidemiology and medicine. <a href="/facts/Precision_and_recall/Jnmmpl8H">Precision and recall</a> are widely used in information retrieval.<a class="footnote-ref" id="fnref:3" href="#fn:3"><sup>3</sup></a>
</p><p>Classifier accuracy depends greatly on the characteristics of the data to be classified. There is no single classifier that works best on all given problems (a phenomenon that may be explained by the <a href="/facts/No_free_lunch_in_search_and_optimization/aNGHqkID">no-free-lunch theorem</a>).
</p>
<h2 id="see-also">See also</h2>
<ul><li><a href="/facts/Class_(disambiguation)/c7SopeCx">Class (disambiguation)</a></li>
<li><a href="/facts/Classified_(disambiguation)/p5EuQc5S">Classified (disambiguation)</a></li>
<li><a href="/facts/Classifier_(disambiguation)/6Y5CxtIq">Classifier (disambiguation)</a></li>
<li><a href="/facts/Cognitive_categorization/R6rWYttP">Cognitive categorization</a></li>
<li><a href="/facts/Data_classification_(disambiguation)/3a8r3g0u">Data classification (disambiguation)</a></li>
<li><a href="/facts/Classification_theorem/NWGgtNm6">Classification theorem</a></li>
<li><a href="/facts/Folk_taxonomy/oj6M3BN0">Folk taxonomy</a></li>
<li><a href="/facts/Fuzzy_classification/jBMVd0nG">Fuzzy classification</a></li></ul>

<h2 id="external-links">External links</h2>

Look up <i>classification</i>, <i>classifications</i>, <i>classifies</i>, <i>classify</i>, or <i>classifying</i> in Wiktionary, the free dictionary.

<ul><li> Media related to Classification at Wikimedia Commons</li></ul>

<h2 id="references">References</h2>

<ol>
<li id="fn:1"><p>"The Classification Society | Scientific Classification Organization". <a href="https://www.theclassificationsociety.org/about/" target="_blank">https://www.theclassificationsociety.org/about/</a> <a href="#fnref:1" class="footnote-back-ref">↩</a></p></li>
<li id="fn:2"><p>"Classification". Internet Encyclopedia of Philosophy. Retrieved 10 January 2025. <a href="https://iep.utm.edu/classification-in-science/" target="_blank">https://iep.utm.edu/classification-in-science/</a> <a href="#fnref:2" class="footnote-back-ref">↩</a></p></li>
<li id="fn:3"><p>David Hand (2012). "Assessing the Performance of Classification Methods". International Statistical Review. 80 (3): 400–414. doi:10.1111/j.1751-5823.2012.00183.x. <a href="/wiki/International_Statistical_Review" target="_blank">/wiki/International_Statistical_Review</a> <a href="#fnref:3" class="footnote-back-ref">↩</a></p></li>
</ol>

Classification open-in-new

Classification