{"id":123544,"date":"2023-06-28T12:41:19","date_gmt":"2023-06-28T15:41:19","guid":{"rendered":"https:\/\/fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/"},"modified":"2023-07-26T15:42:10","modified_gmt":"2023-07-26T18:42:10","slug":"machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning","status":"publish","type":"post","link":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/","title":{"rendered":"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning"},"content":{"rendered":"

<\/p>\n

In summary, recall is a critical metric in the evaluation of machine learning models, particularly in scenarios where identifying positive cases is crucial.<\/h2>\n

It is sensitive to false negatives and prioritizes the correct identification of positive cases.<\/p>\n

It also considers class imbalance in datasets.<\/p>\n

By understanding and monitoring recall, developers and researchers can improve the quality and reliability of models, ensuring appropriate performance for the applications in which they are used.<\/p>\n

Como Calcular o Recall em Modelos de Machine Learning<\/h2>\n

O Recall \u00e9 uma m\u00e9trica fundamental<\/a> na avalia\u00e7\u00e3o de modelos de Machine Learning.<\/p>\n

Ele mede a capacidade do modelo em identificar corretamente os exemplos positivos<\/a> de uma classe.<\/p>\n

\u00c9 especialmente \u00fatil em casos em que os falsos negativos<\/a> s\u00e3o custosos e precisamos minimizar o n\u00famero de casos em que verdadeiros positivos s\u00e3o classificados como negativos.<\/p>\n

Neste artigo, vamos discutir como calcular o Recall em modelos de Machine Learning e sua import\u00e2ncia na avalia\u00e7\u00e3o de modelos.<\/p>\n

Antes de mergulharmos no c\u00e1lculo do Recall, \u00e9 importante entender alguns conceitos b\u00e1sicos.<\/h3>\n

Em um problema de classifica\u00e7\u00e3o bin\u00e1ria, temos duas classes: positiva e negativa.<\/p>\n

O modelo atribui uma classifica\u00e7\u00e3o para cada exemplo – verdadeiro positivo (TP) quando o exemplo \u00e9 positivo e classificado corretamente, falso positivo (FP) quando o exemplo \u00e9 negativo, mas \u00e9 classificado como positivo, verdadeiro negativo (TN) quando o exemplo \u00e9 negativo e classificado corretamente e falso negativo (FN) quando o exemplo \u00e9 positivo, mas \u00e9 classificado como negativo.<\/p>\n

A f\u00f3rmula para calcular o Recall \u00e9 a seguinte:<\/p>\n

Recall = TP \/ (TP + FN)<\/p>\n

Ou seja, o Recall \u00e9 a propor\u00e7\u00e3o dos exemplos positivos corretamente classificados em rela\u00e7\u00e3o ao total de exemplos positivos presentes nos dados.<\/p>\n

Ele varia de 0 a 1, onde 0 indica que o modelo n\u00e3o classifica corretamente nenhum exemplo positivo e 1 indica que todos os exemplos positivos s\u00e3o classificados corretamente.<\/p>\n

Cen\u00e1rios de Uso e Aplica\u00e7\u00f5es do Recall em Machine Learning<\/h2>\n

O Recall tem v\u00e1rias aplica\u00e7\u00f5es em Machine Learning, principalmente em casos onde identificar corretamente os exemplos positivos \u00e9 crucial.<\/p>\n

Alguns cen\u00e1rios de uso do Recall incluem:<\/p>\n

Detec\u00e7\u00e3o de fraudes:<\/h3>\n

Em sistemas de detec\u00e7\u00e3o de fraudes, \u00e9 importante minimizar os falsos negativos, ou seja, identificar corretamente o m\u00e1ximo de casos de fraude<\/a> poss\u00edvel.<\/p>\n

Nesse caso, o Recall seria usado para avaliar a capacidade do modelo em identificar corretamente os casos de fraude.<\/p>\n

Detec\u00e7\u00e3o de doen\u00e7as:<\/h3>\n

Em sistemas de detec\u00e7\u00e3o de doen\u00e7as, como o c\u00e2ncer, \u00e9 fundamental minimizar os falsos negativos, pois classificar erroneamente um paciente como n\u00e3o tendo a doen\u00e7a pode ter consequ\u00eancias graves.<\/p>\n

O Recall \u00e9 usado para avaliar a capacidade do modelo em identificar corretamente os casos positivos.<\/p>\n

Detec\u00e7\u00e3o de spams:<\/h3>\n

Em sistemas de detec\u00e7\u00e3o de spams, \u00e9 essencial minimizar os falsos negativos, ou seja, classificar corretamente o m\u00e1ximo de e-mails spam poss\u00edvel.<\/p>\n

O Recall \u00e9 usado para avaliar a capacidade do modelo em identificar corretamente os e-mails spam.<\/p>\n

Detec\u00e7\u00e3o de anomalias:<\/h3>\n

Em sistemas de detec\u00e7\u00e3o de anomalias, como a detec\u00e7\u00e3o de intrus\u00f5es em redes, \u00e9 importante minimizar os falsos negativos, ou seja, identificar corretamente o m\u00e1ximo de casos de intrus\u00f5es poss\u00edvel.<\/p>\n

Nesse caso, o Recall seria usado para avaliar a capacidade do modelo em identificar corretamente as intrus\u00f5es.<\/p>\n

Em todos esses cen\u00e1rios, o Recall \u00e9 uma m\u00e9trica crucial para avaliar o desempenho do modelo em identificar corretamente os exemplos positivos.<\/p>\n

Conclus\u00e3o<\/h2>\n

O Recall \u00e9 uma m\u00e9trica essencial na avalia\u00e7\u00e3o de modelos de Machine Learning.<\/p>\n

Ele permite medir a capacidade do modelo em identificar corretamente os exemplos positivos de uma classe.<\/p>\n

Em cen\u00e1rios onde os falsos negativos s\u00e3o custosos e precisamos minimizar o n\u00famero de casos em que verdadeiros positivos s\u00e3o classificados como negativos, o Recall se torna ainda mais relevante.<\/p>\n

\u00c9 importante calcular o Recall corretamente e entender suas aplica\u00e7\u00f5es em diferentes cen\u00e1rios de uso.<\/p>\n

Desenvolva a sua carreira hoje mesmo! Conhe\u00e7a a Awari<\/a>.<\/p>\n

A Awari \u00e9 uma plataforma de ensino completa que conta com mentorias individuais, cursos com aulas ao vivo e suporte de carreira para voc\u00ea dar seu pr\u00f3ximo passo profissional.<\/p>\n

Quer aprender mais sobre as t\u00e9cnicas necess\u00e1rias para se tornar um profissional de relev\u00e2ncia e sucesso?<\/p>\n

Conhe\u00e7a nossos cursos<\/a> e desenvolva compet\u00eancias essenciais com jornada personalizada, para desenvolver e evoluir seu curr\u00edculo, o seu pessoal e materiais complementares desenvolvidos por especialistas no mercado!<\/p>\n

<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"

Summary: Machine learning recall is a critical metric for evaluating models. It measures the ability to correctly identify positive cases and is especially useful in scenarios where false negatives are costly. Understanding and monitoring recall allows developers and researchers to improve model quality, ensuring appropriate performance for applications.<\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":[186],"meta":{"inline_featured_image":false,"footnotes":""},"categories":[229],"tags":[],"trilha":[],"class_list":["post-123544","post","type-post","status-publish","format-standard","hentry","category-skills","format-artigos"],"acf":[],"yoast_head":"\nMachine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning - Fluency.io Brasil<\/title>\n<meta name=\"description\" content=\"Summary: Machine learning recall is a critical metric for evaluating models. It measures the ability to correctly identify positive cases and is especially...\" \/>\n<meta name=\"robots\" content=\"noindex, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<meta property=\"og:locale\" content=\"pt_BR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning - Fluency.io Brasil\" \/>\n<meta property=\"og:description\" content=\"Summary: Machine learning recall is a critical metric for evaluating models. It measures the ability to correctly identify positive cases and is especially...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/\" \/>\n<meta property=\"og:site_name\" content=\"Fluency.io Brasil\" \/>\n<meta property=\"article:published_time\" content=\"2023-06-28T15:41:19+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-07-26T18:42:10+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"kaue\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. tempo de leitura\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/\"},\"author\":{\"name\":\"kaue\",\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/#\\\/schema\\\/person\\\/7b3b2b50ba17b7f2ad0cce0a40bfa00a\"},\"headline\":\"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning\",\"datePublished\":\"2023-06-28T15:41:19+00:00\",\"dateModified\":\"2023-07-26T18:42:10+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/\"},\"wordCount\":752,\"commentCount\":0,\"articleSection\":[\"Skills\"],\"inLanguage\":\"pt-BR\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/\",\"url\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/\",\"name\":\"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning - Fluency.io Brasil\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/#website\"},\"datePublished\":\"2023-06-28T15:41:19+00:00\",\"dateModified\":\"2023-07-26T18:42:10+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/#\\\/schema\\\/person\\\/7b3b2b50ba17b7f2ad0cce0a40bfa00a\"},\"description\":\"Summary: Machine learning recall is a critical metric for evaluating models. It measures the ability to correctly identify positive cases and is especially...\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/#breadcrumb\"},\"inLanguage\":\"pt-BR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/blog\\\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"In\u00edcio\",\"item\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/#website\",\"url\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/\",\"name\":\"Fluency.io Brasil\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"pt-BR\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/#\\\/schema\\\/person\\\/7b3b2b50ba17b7f2ad0cce0a40bfa00a\",\"name\":\"kaue\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-BR\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/bdd3958fa53019cfd8f789c0a49a730e7ba40a1d20cb42c9ced7646285842479?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/bdd3958fa53019cfd8f789c0a49a730e7ba40a1d20cb42c9ced7646285842479?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/bdd3958fa53019cfd8f789c0a49a730e7ba40a1d20cb42c9ced7646285842479?s=96&d=mm&r=g\",\"caption\":\"kaue\"},\"url\":\"https:\\\/\\\/homolog.fluency.io\\\/br\\\/author\\\/kaue\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning - Fluency.io Brasil","description":"Summary: Machine learning recall is a critical metric for evaluating models. It measures the ability to correctly identify positive cases and is especially...","robots":{"index":"noindex","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"og_locale":"pt_BR","og_type":"article","og_title":"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning - Fluency.io Brasil","og_description":"Summary: Machine learning recall is a critical metric for evaluating models. It measures the ability to correctly identify positive cases and is especially...","og_url":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/","og_site_name":"Fluency.io Brasil","article_published_time":"2023-06-28T15:41:19+00:00","article_modified_time":"2023-07-26T18:42:10+00:00","twitter_card":"summary_large_image","twitter_misc":{"Escrito por":"kaue","Est. tempo de leitura":"4 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/#article","isPartOf":{"@id":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/"},"author":{"name":"kaue","@id":"https:\/\/homolog.fluency.io\/br\/#\/schema\/person\/7b3b2b50ba17b7f2ad0cce0a40bfa00a"},"headline":"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning","datePublished":"2023-06-28T15:41:19+00:00","dateModified":"2023-07-26T18:42:10+00:00","mainEntityOfPage":{"@id":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/"},"wordCount":752,"commentCount":0,"articleSection":["Skills"],"inLanguage":"pt-BR","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/","url":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/","name":"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning - Fluency.io Brasil","isPartOf":{"@id":"https:\/\/homolog.fluency.io\/br\/#website"},"datePublished":"2023-06-28T15:41:19+00:00","dateModified":"2023-07-26T18:42:10+00:00","author":{"@id":"https:\/\/homolog.fluency.io\/br\/#\/schema\/person\/7b3b2b50ba17b7f2ad0cce0a40bfa00a"},"description":"Summary: Machine learning recall is a critical metric for evaluating models. It measures the ability to correctly identify positive cases and is especially...","breadcrumb":{"@id":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/#breadcrumb"},"inLanguage":"pt-BR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/homolog.fluency.io\/br\/blog\/machine-learning-recall-metrica-de-avaliacao-de-modelos-de-machine-learning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"In\u00edcio","item":"https:\/\/homolog.fluency.io\/br\/"},{"@type":"ListItem","position":2,"name":"Machine Learning Recall: M\u00e9trica de Avalia\u00e7\u00e3o de Modelos de Machine Learning"}]},{"@type":"WebSite","@id":"https:\/\/homolog.fluency.io\/br\/#website","url":"https:\/\/homolog.fluency.io\/br\/","name":"Fluency.io Brasil","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/homolog.fluency.io\/br\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"pt-BR"},{"@type":"Person","@id":"https:\/\/homolog.fluency.io\/br\/#\/schema\/person\/7b3b2b50ba17b7f2ad0cce0a40bfa00a","name":"kaue","image":{"@type":"ImageObject","inLanguage":"pt-BR","@id":"https:\/\/secure.gravatar.com\/avatar\/bdd3958fa53019cfd8f789c0a49a730e7ba40a1d20cb42c9ced7646285842479?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/bdd3958fa53019cfd8f789c0a49a730e7ba40a1d20cb42c9ced7646285842479?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/bdd3958fa53019cfd8f789c0a49a730e7ba40a1d20cb42c9ced7646285842479?s=96&d=mm&r=g","caption":"kaue"},"url":"https:\/\/homolog.fluency.io\/br\/author\/kaue\/"}]}},"_links":{"self":[{"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/posts\/123544","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/comments?post=123544"}],"version-history":[{"count":0,"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/posts\/123544\/revisions"}],"wp:attachment":[{"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/media?parent=123544"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/categories?post=123544"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/tags?post=123544"},{"taxonomy":"format","embeddable":true,"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/format?post=123544"},{"taxonomy":"trilha","embeddable":true,"href":"https:\/\/homolog.fluency.io\/br\/wp-json\/wp\/v2\/trilha?post=123544"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}