{"id":9004111223080332,"date":"2022-01-12T18:02:18","date_gmt":"2022-01-12T22:02:18","guid":{"rendered":"https:\/\/www.pragmaticinstitute.com\/?p=9004111222994422"},"modified":"2022-02-22T16:32:24","modified_gmt":"2022-02-22T20:32:24","slug":"designing-ai-models-to-extract-insights","status":"publish","type":"resources","link":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/","title":{"rendered":"Designing AI Models to Extract Insights"},"content":{"rendered":"<p><span style=\"font-weight: 400;\">In the first white paper of this series, \u201c<a href=\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/making-the-leap-from-ai-investments-to-business-results\/\">Making the Leap from AI Investments to Business Results<\/a>,\u201d I discussed a holistic approach to designing AI solutions and driving value for your customers and shareholders.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Here\u2019s the framework used to secure return on investment from your AI projects:<\/span><\/p>\n<p><img fetchpriority=\"high\" decoding=\"async\" class=\"aligncenter wp-image-9004111222994507\" src=\"https:\/\/www.pragmaticinstitute.com\/wp-content\/uploads\/2022\/01\/Capture-300x73.png\" alt=\"\" width=\"1800\" height=\"440\" srcset=\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-300x73.png 300w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-1024x250.png 1024w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-768x188.png 768w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-600x147.png 600w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture.png 1203w\" sizes=\"(max-width: 1800px) 100vw, 1800px\" \/><\/p>\n<p><b>1. Align with Strategic Objectives \u2013<\/b><span style=\"font-weight: 400;\"> Before investing in any AI projects, start with the business objectives. Work your way to the AI projects or use cases that provide insights to accelerate achieving the strategic objectives for the company. This approach ensures that you are investing in the right AI projects for the company from the start.<\/span><\/p>\n<p><b>2. Design to Predict <\/b><span style=\"font-weight: 400;\">\u2013 Before you build out the analytics model, thoroughly validate the approach(es) so you don\u2019t have to make costly course corrections down the road. Build the models to predict the outcomes you\u2019re looking for. Plan early to build the visualization of the model insights for the audiences that need to take an action.\u00a0<\/span><\/p>\n<p><b>3. Drive Systemic Action <\/b><span style=\"font-weight: 400;\">\u2013 Insight without any action is a wasted effort. Plan on change management to secure buy-in from all levels within the organization. Refine business processes and align training, incentives, and performance management, so all relevant operations in the business are aligned to act on the insights.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Let&#8217;s dive deeper into the second element of the framework, &#8220;design to predict.&#8221; <\/span><span style=\"font-weight: 400;\">Why is this critical?\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The most common reasons that AI implementations do not achieve their intended results include:<\/span><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\">Approach<\/span><span style=\"font-weight: 400;\">: Lack of clear strategy and understanding of what is achievable<\/span><\/li>\n<li><b>Design<\/b><b>: Poor model design, data and governance issues and algorithm bias<\/b><\/li>\n<li><span style=\"font-weight: 400;\">Implementation<\/span><span style=\"font-weight: 400;\">: Limited internal support for full implementation<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Trust<\/span><span style=\"font-weight: 400;\">: Lack of trust in the insights<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Action<\/span><span style=\"font-weight: 400;\">: Inability to translate insights to action<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">It is important to ensure that the model is aligned to achieve the business objectives and is designed to accurately predict the desired outcomes. <\/span><span style=\"font-weight: 400;\">Consider the following four-step process for<\/span><b> <\/b><span style=\"font-weight: 400;\">design to predict<\/span><span style=\"font-weight: 400;\">:<\/span><\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-9004111222994656 size-large\" src=\"https:\/\/www.pragmaticinstitute.com\/wp-content\/uploads\/2022\/01\/Capture-4-1024x388.png\" alt=\"\" width=\"1024\" height=\"388\" srcset=\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-4-1024x388.png 1024w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-4-300x114.png 300w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-4-768x291.png 768w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-4-600x227.png 600w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture-4.png 1230w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/p>\n<h2><b>1. Planning to Predict\u00a0<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">Before delving into and investing significant time and money to build AI-based models, it is crucial to build a proof of concept, or &#8220;POC.&#8221; But how do you build an effective POC? The first step is to determine the overall objectives, the current process, what data is available and (most importantly) the ability of the available data to predict the desired outcomes.<\/span><\/p>\n<p><span style=\"font-weight: 400;\"> To that end, the planning to predict is a structured framework to determine the model&#8217;s viability before investing a significant amount of time in building the model(s). Here is the framework:<\/span><\/p>\n<p><img decoding=\"async\" class=\"aligncenter wp-image-9004111222994625\" src=\"https:\/\/www.pragmaticinstitute.com\/wp-content\/uploads\/2022\/01\/Capture3-300x154.png\" alt=\"\" width=\"1800\" height=\"926\" srcset=\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture3-300x154.png 300w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture3-1024x527.png 1024w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture3-768x395.png 768w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture3-600x309.png 600w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/Capture3.png 1481w\" sizes=\"(max-width: 1800px) 100vw, 1800px\" \/><\/p>\n<h3><b>1.1 Create a Process Map<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Develop a view of the current process outlining the data flow and money flow. The flow of money often provides insight into value creation in the process; however, you may need to create a view highlighting where value is created explicitly. Define key actions in the process and the critical decision points. <\/span><span style=\"font-weight: 400;\">This is important to prioritize the predictions to support the decision points in the process. Most of this information can be derived through interviews of key personnel and reviews of existing materials.<\/span><\/p>\n<h3><b>1.2 Quantify the Process\u00a0<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Develop a quantified view of the process by identifying <strong>key<\/strong> <\/span><b>performance metrics<\/b><span style=\"font-weight: 400;\"> at each critical decision point. Determine both the current metrics and desired metrics. Desired metrics can be based on available benchmarks wherever possible. Craft the <\/span><b>desired outcomes<\/b><span style=\"font-weight: 400;\"> around strategic objectives.\u00a0<\/span><\/p>\n<h3><b>1.3 Extract Data\u00a0<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Collect relevant and representative data across the process map. Consider both structured and unstructured data. Data needs to be cleansed and transformed into the required formats and structure suitable for analysis. Consider the following sources of data:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Data within organizational systems readily accessible (e.g., CRM, databases, etc.)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Data within the organization not readily accessible (e.g., PDFs, pictures, surveys, etc.)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Data outside the organization or publicly available data (e.g., average income levels by zip code available from data published by the IRS) \u2014This data could be used to augment data within the organization to provide richer insights.<\/span><\/li>\n<\/ul>\n<h3><b>1.4 Analyze Data\u00a0<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Conduct a preliminary and manual analysis, considering that this is towards a POC. In this preliminary step, this analysis is considered \u201cmanual\u201d as the data is not yet linked to the source systems. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">It is essentially a static model where the data from the previous step is analyzed across potential AI models to determine predicted outcomes. Analysis tools used at this stage could be Microsoft Excel or a statistical software suite such as IBM\u2019s SPSS, JMP, SAS, MATLAB, etc. Use multiple analysis models to determine the models that best fit your use case.<\/span><\/p>\n<h3><b>1.05 Assess Predictability<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Determine the list of data fields and variables that represent the critical decision points and desired outcomes. For each model, assess the degree to which the data predicts the outcomes. Based on this, you should prioritize the AI models and the data elements that best predict the desired outcomes.\u00a0<\/span><\/p>\n<blockquote><p>By planning for repeatability early in the process, companies can save money and time by implementing a solution designed for scalability from the ground up.<\/p><\/blockquote>\n<p><span style=\"font-weight: 400;\">Based on the results from this step, you can review the process map, refine data collection and the analysis to improve the predictability of the data and the models to meet your needs.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">An important point to consider in the planning to predict and subsequent model development steps is &#8220;repeatability.&#8221; Often, when the POC is deemed a success, companies accelerate efforts to build the production models and systems too quickly without paying sufficient attention to the ability of the solution design to scale. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">By planning for repeatability early in the process, companies can save money and time by implementing a solution designed for scalability from the ground up.<\/span><\/p>\n<h1><b>2. Model Development\u00a0<\/b><\/h1>\n<p><span style=\"font-weight: 400;\">Several standard AI models can be used to identify patterns to predict outcomes. Models include Linear Regression, Deep Neural Networks, Bayesian Algorithms, etc. After the planning to predict step, you should have a good idea of the analytical model that best represents your particular use case and the likely predictors. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Set aside a portion of the data to conduct a blind test of the model(s) and utilize the remaining data to train the model(s). Develop the selected model(s) using a standard coding platform such as Python. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Test the model with the test data and refine the configurations to improve prediction accuracy. <\/span><span style=\"font-weight: 400;\">Ideally, define an API (Application Programming Interface) for the model to simplify integration and future upgrades. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Ensure the models are designed with attention to data and governance requirements while incorporating safeguards to avoid algorithm or design bias.<\/span><\/p>\n<h1><b>3. Deployment and Integration<\/b><\/h1>\n<p><span style=\"font-weight: 400;\">Build and integrate the model into the production systems as appropriate. Design and implement the code to extract and transform the required data on a dynamic basis and integrate the model with the data sources. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">You may need to integrate with other standard APIs to access data from CRM systems, IOT systems, phone systems, etc.\u00a0<\/span><\/p>\n<h1><b>4. Visualization\u00a0\u00a0<\/b><\/h1>\n<p><span style=\"font-weight: 400;\">Suppose you want to take action based on insights from the analytical models. In that case, you will need to provide visibility of relevant data and insights to the specific audiences who need to take action and\/or be aware of the changes. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Define the data elements that need to be tracked and utilized to trigger actions. Data elements could include historical data, thresholds, alerts, data that would need to be actioned, etc. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Define the actions that need to be taken at each decision point and the owners across the organization. Design and implement the visualization dashboards organized by type of audience and owner.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The design to predict process will help improve your odds of success by planning effective models to identify patterns and uncover insights so you can take relevant actions.\u00a0<\/span><\/p>\n<p>&nbsp;<\/p>\n<p style=\"text-align: center;\">* * *<\/p>\n<p><em><img loading=\"lazy\" decoding=\"async\" class=\" wp-image-9004111222960021 alignleft\" src=\"https:\/\/www.pragmaticinstitute.com\/wp-content\/uploads\/2021\/11\/sciata-logo.jpg\" alt=\"\" width=\"340\" height=\"81\" srcset=\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2021\/11\/sciata-logo.jpg 557w, https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2021\/11\/sciata-logo-300x72.jpg 300w\" sizes=\"(max-width: 340px) 100vw, 340px\" \/>This is the fourth white paper in <a href=\"https:\/\/pragmaticinstitute.com\/\" target=\"_blank\" rel=\"noopener\">Pragmatic Institute\u2019<\/a>s series by Sciata President\u00a0<a href=\"https:\/\/www.linkedin.com\/in\/harishk-sciata\/\" target=\"_blank\" rel=\"noopener\">Harish Krishnamurthy<\/a> on ensuring ROI from artificial intelligence, transforming insights into action, and driving a cultural change in how your organization leverages data. Read the previous pieces: 1) <a href=\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/making-the-leap-from-ai-investments-to-business-results\/\" target=\"_blank\" rel=\"noopener\">\u201cMaking the Leap from AI Investments to Business Results,\u201d<\/a>\u00a0 2) <a href=\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/aligning-it-and-business-strategy-for-project-success\/\" target=\"_blank\" rel=\"noopener\">\u201cAligning IT and Business Strategy for Project Success,\u201d<\/a> 3) <a href=\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/using-ai-to-maximize-customer-lifetime-value\/\">&#8220;Using AI to Maximize Customer Lifetime Value,&#8221;<\/a> and the final one, 5) <a href=\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/transforming-insights-into-actions-and-business-results\/\">&#8220;Transforming AI Insights into Actions.&#8221;<\/a><\/em><\/p>\n<p><em><strong><a href=\"https:\/\/www.pragmaticinstitute.com\/data\/private-training\">Learn how Pragmatic Institute can\u00a0train your data team<\/a>\u00a0to deliver critical insights that power business strategy.<\/strong><\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>AI implementations often fail to achieve their intended results because of poor model design. This white paper dives deep into the &#8220;design to predict&#8221; phase of Harish Krishnamurthy&#8217;s framework for securing ROI from AI projects.<\/p>\n","protected":false},"author":9004111222834625,"featured_media":9004111222994693,"menu_order":0,"template":"","categories":[9004111222509931],"tags":[],"content-series":[],"content-format":[9004111223037711],"framework-box":[],"vertical":[132],"ppma_author":[9004111222875212],"class_list":["post-9004111223080332","resources","type-resources","status-publish","has-post-thumbnail","hentry","category-data-science","content-format-article","vertical-data","author-harish-krishnamurthy"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.2 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Designing AI Models to Extract Insights | Pragmatic Institute<\/title>\n<meta name=\"description\" content=\"One of the most common reasons for why AI implementations do not achieve their intended results is poor model design.\" \/>\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.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Designing AI Models to Extract Insights | Pragmatic Institute\" \/>\n<meta property=\"og:description\" content=\"One of the most common reasons for why AI implementations do not achieve their intended results is poor model design.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/\" \/>\n<meta property=\"og:site_name\" content=\"Pragmatic Institute - Resources\" \/>\n<meta property=\"article:modified_time\" content=\"2022-02-22T20:32:24+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"801\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/\",\"url\":\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/\",\"name\":\"Designing AI Models to Extract Insights | Pragmatic Institute\",\"isPartOf\":{\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg\",\"datePublished\":\"2022-01-12T22:02:18+00:00\",\"dateModified\":\"2022-02-22T20:32:24+00:00\",\"description\":\"One of the most common reasons for why AI implementations do not achieve their intended results is poor model design.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#primaryimage\",\"url\":\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg\",\"contentUrl\":\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg\",\"width\":1200,\"height\":801},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.pragmaticinstitute.com\/resources\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Resources\",\"item\":\"https:\/\/www.pragmaticinstitute.com\/resources\/resources\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Designing AI Models to Extract Insights\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/#website\",\"url\":\"https:\/\/www.pragmaticinstitute.com\/resources\/\",\"name\":\"Pragmatic Institute\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/#organization\"},\"alternateName\":\"Pragmatic\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.pragmaticinstitute.com\/resources\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/#organization\",\"name\":\"Pragmatic Institute\",\"url\":\"https:\/\/www.pragmaticinstitute.com\/resources\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2021\/09\/The_Pragmatic_Institute_Stacked_Logo.png\",\"contentUrl\":\"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2021\/09\/The_Pragmatic_Institute_Stacked_Logo.png\",\"width\":216,\"height\":224,\"caption\":\"Pragmatic Institute\"},\"image\":{\"@id\":\"https:\/\/www.pragmaticinstitute.com\/resources\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Designing AI Models to Extract Insights | Pragmatic Institute","description":"One of the most common reasons for why AI implementations do not achieve their intended results is poor model design.","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.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/","og_locale":"en_US","og_type":"article","og_title":"Designing AI Models to Extract Insights | Pragmatic Institute","og_description":"One of the most common reasons for why AI implementations do not achieve their intended results is poor model design.","og_url":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/","og_site_name":"Pragmatic Institute - Resources","article_modified_time":"2022-02-22T20:32:24+00:00","og_image":[{"width":1200,"height":801,"url":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/","url":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/","name":"Designing AI Models to Extract Insights | Pragmatic Institute","isPartOf":{"@id":"https:\/\/www.pragmaticinstitute.com\/resources\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#primaryimage"},"image":{"@id":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#primaryimage"},"thumbnailUrl":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg","datePublished":"2022-01-12T22:02:18+00:00","dateModified":"2022-02-22T20:32:24+00:00","description":"One of the most common reasons for why AI implementations do not achieve their intended results is poor model design.","breadcrumb":{"@id":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#primaryimage","url":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg","contentUrl":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2022\/01\/pexels-christina-morillo-1181263-scaled-e1642022526642.jpg","width":1200,"height":801},{"@type":"BreadcrumbList","@id":"https:\/\/www.pragmaticinstitute.com\/resources\/articles\/data\/designing-ai-models-to-extract-insights\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pragmaticinstitute.com\/resources\/"},{"@type":"ListItem","position":2,"name":"Resources","item":"https:\/\/www.pragmaticinstitute.com\/resources\/resources\/"},{"@type":"ListItem","position":3,"name":"Designing AI Models to Extract Insights"}]},{"@type":"WebSite","@id":"https:\/\/www.pragmaticinstitute.com\/resources\/#website","url":"https:\/\/www.pragmaticinstitute.com\/resources\/","name":"Pragmatic Institute","description":"","publisher":{"@id":"https:\/\/www.pragmaticinstitute.com\/resources\/#organization"},"alternateName":"Pragmatic","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.pragmaticinstitute.com\/resources\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.pragmaticinstitute.com\/resources\/#organization","name":"Pragmatic Institute","url":"https:\/\/www.pragmaticinstitute.com\/resources\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.pragmaticinstitute.com\/resources\/#\/schema\/logo\/image\/","url":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2021\/09\/The_Pragmatic_Institute_Stacked_Logo.png","contentUrl":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-content\/uploads\/sites\/6\/2021\/09\/The_Pragmatic_Institute_Stacked_Logo.png","width":216,"height":224,"caption":"Pragmatic Institute"},"image":{"@id":"https:\/\/www.pragmaticinstitute.com\/resources\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/resources\/9004111223080332","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/resources"}],"about":[{"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/types\/resources"}],"author":[{"embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/users\/9004111222834625"}],"version-history":[{"count":0,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/resources\/9004111223080332\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/media\/9004111222994693"}],"wp:attachment":[{"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/media?parent=9004111223080332"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/categories?post=9004111223080332"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/tags?post=9004111223080332"},{"taxonomy":"content-series","embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/content-series?post=9004111223080332"},{"taxonomy":"content-format","embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/content-format?post=9004111223080332"},{"taxonomy":"framework-box","embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/framework-box?post=9004111223080332"},{"taxonomy":"vertical","embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/vertical?post=9004111223080332"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.pragmaticinstitute.com\/resources\/wp-json\/wp\/v2\/ppma_author?post=9004111223080332"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}