{"id":11261,"date":"2022-08-02T09:23:51","date_gmt":"2022-08-02T08:23:51","guid":{"rendered":"https:\/\/ee.yelkdev.site\/?p=11261"},"modified":"2024-12-10T02:08:56","modified_gmt":"2024-12-10T02:08:56","slug":"how-to-monitor-mlops-monitoring-principles","status":"publish","type":"post","link":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/","title":{"rendered":"The importance of observability in MLOps"},"content":{"rendered":"<p>ML solutions need to be monitored for errors and performance just like any other software solution. ML driven products typically need to meet two key observability concerns:<\/p>\n<ul>\n<li aria-level=\"1\">Monitoring the model as a software product that includes metrics such as the number of prediction requests, its latency and error rate.<\/li>\n<li aria-level=\"1\">Monitoring model prediction performance or efficacy, such as f1 score for classification or mean squared error for regression.<\/li>\n<\/ul>\n<h2>Monitoring as a Software Product<\/h2>\n<p>As a software product, monitoring can be accomplished using existing off the shelf tooling such as Prometheus, Graphite or AWS CloudWatch.\u00a0 If the solution is created using auto-generated ML\u00a0 this becomes even more important. Model code may be generated that slows down predictions enough to cause timeouts and stop user transactions from processing.<\/p>\n<p>You should ideally monitor:<\/p>\n<ul>\n<li aria-level=\"1\">Availability<\/li>\n<li aria-level=\"1\">Request\/Response timings<\/li>\n<li aria-level=\"1\">Throughput<\/li>\n<li aria-level=\"1\">Resource usage<\/li>\n<\/ul>\n<p>Alerting should be set up across these metrics to catch issues before they become critical.<\/p>\n<h2>Monitoring model prediction performance<\/h2>\n<p>ML models are trained on data that\u2019s available at a certain point in time. Data drift or concept drift \u00a0happens when the input data changes its distributions, which can affect the performance of the model. Let\u2019s imagine we have a user signup model that forecasts the mean basket sales of users for an online merchant.\u00a0 One of the input variables the model depends on is the age of the new users.\u00a0 As we can see from the distributions below, the age of new users has shifted from August to September 2021.<\/p>\n<img decoding=\"async\" class=\"aligncenter wp-image-11262 size-full\" src=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitor-graph-1.png\" alt=\"\" width=\"480\" height=\"360\" srcset=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitor-graph-1.png 480w, https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitor-graph-1-300x225.png 300w\" sizes=\"(max-width: 480px) 100vw, 480px\" \/>\n<p>It is important to monitor the live output of your models to ensure they are still accurate against new data as it arrives. This monitoring can provide important cues when to retrain your models, and dashboards can give additional insight into seasonal events or data skew.<\/p>\n<p>There are a number of metrics which can be useful including:<\/p>\n<ul>\n<li aria-level=\"1\">Precision\/Recall\/F1 Score.<\/li>\n<li aria-level=\"1\">Model score outputs.<\/li>\n<li aria-level=\"1\">User feedback labels or downstream actions<\/li>\n<li aria-level=\"1\">Feature monitoring (Data Quality outputs such as histograms, variance, completeness).<\/li>\n<\/ul>\n<p>The right metrics for your model will depend on the purpose of the model and the ability to access the performance data in the right time frame.<\/p>\n<p>Below is an example of a classification performance dashboard that tracks the precision and recall over time. As you can see, the model\u2019s performance is becoming more erratic and degrading from 1st April onwards.<\/p>\n<img decoding=\"async\" class=\"aligncenter wp-image-11268 size-full\" src=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitoing-content-image.png\" alt=\"\" width=\"512\" height=\"138\" srcset=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitoing-content-image.png 512w, https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitoing-content-image-300x81.png 300w\" sizes=\"(max-width: 512px) 100vw, 512px\" \/>\n<p>Alerting should be set up on model accuracy metrics to catch any sudden regressions that may occur. This has been seen on projects where old models have suddenly failed against new data (fraud risking can become less accurate as new attack vectors are discovered), or where an auto ML solution has generated buggy model code. Some ideas on alerting are:<\/p>\n<ul>\n<li aria-level=\"1\">% decrease in precision or recall.<\/li>\n<li aria-level=\"1\">variance change in model score or outputs.<\/li>\n<li aria-level=\"1\">changes in dependent user outputs e.g. number of search click throughs for a recommendation engine.<\/li>\n<\/ul>\n<p>The chart below illustrates that model A\u2019s performance degrades over time.\u00a0 A new challenger model, B, is re-trained on more recent data and becomes a candidate for promotion.<\/p>\n<img decoding=\"async\" class=\"aligncenter wp-image-11263 size-full\" src=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitor-graph-2.png\" alt=\"\" width=\"480\" height=\"360\" srcset=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitor-graph-2.png 480w, https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/MLOps-Monitor-graph-2-300x225.png 300w\" sizes=\"(max-width: 480px) 100vw, 480px\" \/>\n<h2>Data Quality<\/h2>\n<p>A model is only as good as the data it\u2019s given, so instrumenting the quality of input data is crucial for ML products. Data quality includes the volume of records, the completeness of input variables and their ranges. If data quality degrades, this will cause your model to deteriorate.<\/p>\n<p>To read more about monitoring and metrics for MLOps, download our new <a href=\"https:\/\/www.equalexperts.com\/our-services\/data\/mlops\/\">MLOps playbook<\/a>, \u201cOperationalising Machine Learning\u201d, which provides comprehensive guidance for operations and AI teams in adopting best practice.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>AI and machine learning models are just like other software products and require monitoring and observability.  Read on to discover four essential principles of ML product monitoring and how to implement them. <\/p>\n","protected":false},"author":188,"featured_media":11267,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"categories":[3],"tags":[99,276,265,291],"location":[397],"class_list":["post-11261","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tech-focus","tag-ai","tag-mlmodels","tag-mlops","tag-observability"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.9 (Yoast SEO v25.9) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>The importance of observability in MLOps | Equal Experts<\/title>\n<meta name=\"description\" content=\"Over time, ML models can become less effective as data changes. Here\u2019s what you should be monitoring to spot and resolve those changes early.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The importance of observability in MLOps\" \/>\n<meta property=\"og:description\" content=\"AI and machine learning models are just like other software products and require monitoring and observability. Read on to discover four essential principles of ML product monitoring and how to implement them.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/\" \/>\n<meta property=\"og:site_name\" content=\"Equal Experts\" \/>\n<meta property=\"article:published_time\" content=\"2022-08-02T08:23:51+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-10T02:08:56+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/fb-05monitoring-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1201\" \/>\n\t<meta property=\"og:image:height\" content=\"631\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Austin Poulton\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"The importance of observability in MLOps\" \/>\n<meta name=\"twitter:description\" content=\"AI and machine learning models are just like other software products and require monitoring and observability. Read on to discover four essential principles of ML product monitoring and how to implement them.\" \/>\n<meta name=\"twitter:creator\" content=\"@EqualExperts\" \/>\n<meta name=\"twitter:site\" content=\"@EqualExperts\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Austin Poulton\" \/>\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:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/\"},\"author\":{\"name\":\"Austin Poulton\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/person\/b8f1eee0457d32825972a5fec3a7b4a1\"},\"headline\":\"The importance of observability in MLOps\",\"datePublished\":\"2022-08-02T08:23:51+00:00\",\"dateModified\":\"2024-12-10T02:08:56+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/\"},\"wordCount\":594,\"publisher\":{\"@id\":\"https:\/\/www.equalexperts.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png\",\"keywords\":[\"AI\",\"mlmodels\",\"mlops\",\"observability\"],\"articleSection\":[\"Tech Focus\"],\"inLanguage\":\"en-GB\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/\",\"url\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/\",\"name\":\"The importance of observability in MLOps | Equal Experts\",\"isPartOf\":{\"@id\":\"https:\/\/www.equalexperts.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png\",\"datePublished\":\"2022-08-02T08:23:51+00:00\",\"dateModified\":\"2024-12-10T02:08:56+00:00\",\"description\":\"Over time, ML models can become less effective as data changes. Here\u2019s what you should be monitoring to spot and resolve those changes early.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage\",\"url\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png\",\"contentUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png\",\"width\":1201,\"height\":515},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.equalexperts.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"The importance of observability in MLOps\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.equalexperts.com\/#website\",\"url\":\"https:\/\/www.equalexperts.com\/\",\"name\":\"Equal Experts\",\"description\":\"Making Software. Better.\",\"publisher\":{\"@id\":\"https:\/\/www.equalexperts.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.equalexperts.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.equalexperts.com\/#organization\",\"name\":\"Equal Experts\",\"url\":\"https:\/\/www.equalexperts.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg\",\"contentUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg\",\"width\":719,\"height\":340,\"caption\":\"Equal Experts\"},\"image\":{\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/EqualExperts\",\"https:\/\/www.linkedin.com\/company\/equal-experts\/?viewAsMember=true\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/person\/b8f1eee0457d32825972a5fec3a7b4a1\",\"name\":\"Austin Poulton\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/2ebd67ab7918a6c5ad94656fb9058ad51a8a933cf969048482731aea82f78562?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/2ebd67ab7918a6c5ad94656fb9058ad51a8a933cf969048482731aea82f78562?s=96&d=mm&r=g\",\"caption\":\"Austin Poulton\"}}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"The importance of observability in MLOps | Equal Experts","description":"Over time, ML models can become less effective as data changes. Here\u2019s what you should be monitoring to spot and resolve those changes early.","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:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/","og_locale":"en_GB","og_type":"article","og_title":"The importance of observability in MLOps","og_description":"AI and machine learning models are just like other software products and require monitoring and observability. Read on to discover four essential principles of ML product monitoring and how to implement them.","og_url":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/","og_site_name":"Equal Experts","article_published_time":"2022-08-02T08:23:51+00:00","article_modified_time":"2024-12-10T02:08:56+00:00","og_image":[{"width":1201,"height":631,"url":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/fb-05monitoring-1.png","type":"image\/png"}],"author":"Austin Poulton","twitter_card":"summary_large_image","twitter_title":"The importance of observability in MLOps","twitter_description":"AI and machine learning models are just like other software products and require monitoring and observability. Read on to discover four essential principles of ML product monitoring and how to implement them.","twitter_creator":"@EqualExperts","twitter_site":"@EqualExperts","twitter_misc":{"Written by":"Austin Poulton","Estimated reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#article","isPartOf":{"@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/"},"author":{"name":"Austin Poulton","@id":"https:\/\/www.equalexperts.com\/#\/schema\/person\/b8f1eee0457d32825972a5fec3a7b4a1"},"headline":"The importance of observability in MLOps","datePublished":"2022-08-02T08:23:51+00:00","dateModified":"2024-12-10T02:08:56+00:00","mainEntityOfPage":{"@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/"},"wordCount":594,"publisher":{"@id":"https:\/\/www.equalexperts.com\/#organization"},"image":{"@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage"},"thumbnailUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png","keywords":["AI","mlmodels","mlops","observability"],"articleSection":["Tech Focus"],"inLanguage":"en-GB"},{"@type":"WebPage","@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/","url":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/","name":"The importance of observability in MLOps | Equal Experts","isPartOf":{"@id":"https:\/\/www.equalexperts.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage"},"image":{"@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage"},"thumbnailUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png","datePublished":"2022-08-02T08:23:51+00:00","dateModified":"2024-12-10T02:08:56+00:00","description":"Over time, ML models can become less effective as data changes. Here\u2019s what you should be monitoring to spot and resolve those changes early.","breadcrumb":{"@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#primaryimage","url":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png","contentUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2022\/08\/lead-img-05monitoring-1.png","width":1201,"height":515},{"@type":"BreadcrumbList","@id":"https:\/\/www.equalexperts.com\/blog\/tech-focus\/how-to-monitor-mlops-monitoring-principles\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.equalexperts.com\/"},{"@type":"ListItem","position":2,"name":"The importance of observability in MLOps"}]},{"@type":"WebSite","@id":"https:\/\/www.equalexperts.com\/#website","url":"https:\/\/www.equalexperts.com\/","name":"Equal Experts","description":"Making Software. Better.","publisher":{"@id":"https:\/\/www.equalexperts.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.equalexperts.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/www.equalexperts.com\/#organization","name":"Equal Experts","url":"https:\/\/www.equalexperts.com\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/","url":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg","contentUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg","width":719,"height":340,"caption":"Equal Experts"},"image":{"@id":"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/EqualExperts","https:\/\/www.linkedin.com\/company\/equal-experts\/?viewAsMember=true"]},{"@type":"Person","@id":"https:\/\/www.equalexperts.com\/#\/schema\/person\/b8f1eee0457d32825972a5fec3a7b4a1","name":"Austin Poulton","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.equalexperts.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/2ebd67ab7918a6c5ad94656fb9058ad51a8a933cf969048482731aea82f78562?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2ebd67ab7918a6c5ad94656fb9058ad51a8a933cf969048482731aea82f78562?s=96&d=mm&r=g","caption":"Austin Poulton"}}]}},"_links":{"self":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/posts\/11261","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/users\/188"}],"replies":[{"embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/comments?post=11261"}],"version-history":[{"count":0,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/posts\/11261\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/media\/11267"}],"wp:attachment":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/media?parent=11261"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/categories?post=11261"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/tags?post=11261"},{"taxonomy":"location","embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/location?post=11261"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}