"}],"short_description":"Introducing USA Geodemographic Embeddings: reusable location context for similarity search, clustering, and GeoAI in ArcGIS.","flexible_content":[{"acf_fc_layout":"content","content":"Most spatial analysis projects begin long before the analysis itself.<\/p>\n
Before you can find similar places such as affordable neighborhoods or build a predictive model for tasks such as estimating house prices, or even explore spatial patterns across communities, you first need location context. That often means gathering a plethora of geospatial datasets spanning across demographics, socioeconomics, and a multitude of other domains, and then figuring out how to bring them together into a usable contextual dataset for your applications.<\/p>\n
For many workflows, preparing the data can take as much effort as the analysis. But what if that location context was already available?<\/p>\n
In this year\u2019s Esri User Conference (July 2026), we introduce USA Geodemographic Embeddings<\/a>, a new layer in ArcGIS Living Atlas of the World<\/a> that captures demographic, housing, socioeconomic, and environmental characteristics for locations across the contiguous United States, Hawaii, and Alaska at the Uber H3 resolution 7 hex-bin geometry.<\/p>\n Designed for spatial analysis, machine learning, and GeoAI workflows, the embeddings provide a ready-to-use and reusable representation of geodemographic context that can be applied across a wide range of tasks directly in ArcGIS Pro.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2975936,"id":2975936,"title":"Figure 1","filename":"EsriBlog0N-scaled.png","filesize":2623017,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-scaled.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/what-if-location-context-came-built-in-introducing-usa-geodemographic-embeddings\/esriblog0n","alt":"USA Geodemographic Embeddings visualized as H3 hexagons showing geodemographic patterns across the United States.","author":"430728","description":"","caption":"A single dimension of the USA Geodemographic Embeddings displayed as a colorful H3 resolution 7 hex-bin surface, revealing broad geodemographic patterns across the contiguous United States.","name":"esriblog0n","status":"inherit","uploaded_to":2975935,"date":"2026-07-09 12:18:36","modified":"2026-07-09 12:19:05","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":2560,"height":1545,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-scaled.png","medium-width":432,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-scaled.png","medium_large-width":768,"medium_large-height":464,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-scaled.png","large-width":1790,"large-height":1080,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-1536x927.png","1536x1536-width":1536,"1536x1536-height":927,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-2048x1236.png","2048x2048-width":2048,"2048x2048-height":1236,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-770x465.png","card_image-width":770,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog0N-1789x1080.png","wide_image-width":1789,"wide_image-height":1080}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":" Imagine you’re exploring an affordable place in your neighborhood and want to find similar places elsewhere in the country.<\/p>\n What are the steps that you\u2019d follow to do this?<\/p>\n You\u2019d probably select dozens of variables for describing affordable localities such as median family income, monthly housing costs, and so on. Then decide how much each variable should matter, followed by standardizing all the values. Finally, you\u2019d end up building a custom similarity model.<\/p>\n With USA Geodemographic Embeddings, you can start with just the place. Yes, that\u2019s all you need.<\/p>\n In an example workflow, a few embedding hex-bins covering some affordable locations near Utica, New York, (shown with green polygons) are used as query features for finding similar locations.<\/p>\n Using embedding-based similarity search with the Find Similar Features Using Embeddings<\/a> tool, ArcGIS Pro identifies affordable areas in other states (shown with yellow polygons) that share similar underlying geodemographic characteristics. You can also take a look at the actual Location Affordability Index<\/a> map, in shades of purple for comparison (darker shades indicate more affordability).<\/p>\n The result isn’t just geographic proximity\u2014it’s contextual similarity.<\/p>\n Whether you’re evaluating retail markets, studying neighborhoods, or exploring comparable communities, the same workflow with USA Geodemographic Embeddings can help answer your question\u2014where are places like this one?<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2975937,"id":2975937,"title":"Figure 2","filename":"EsriBlog1.png","filesize":691122,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/what-if-location-context-came-built-in-introducing-usa-geodemographic-embeddings\/esriblog1","alt":"Embedding-based similarity search highlighting locations with similar geodemographic characteristics.","author":"430728","description":"","caption":"The Find Similar Features Using Embeddings tool highlights locations similar to the query features based on the underlying geodemographic patterns encoded in the USA Geodemographic Embeddings layer.","name":"esriblog1","status":"inherit","uploaded_to":2975935,"date":"2026-07-09 12:19:55","modified":"2026-07-09 12:20:11","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1646,"height":820,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1.png","medium-width":464,"medium-height":231,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1.png","medium_large-width":768,"medium_large-height":383,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1.png","large-width":1646,"large-height":820,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1-1536x765.png","1536x1536-width":1536,"1536x1536-height":765,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1.png","2048x2048-width":1646,"2048x2048-height":820,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1-826x411.png","card_image-width":826,"card_image-height":411,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog1.png","wide_image-width":1646,"wide_image-height":820}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":" Predictive models heavily depend on the explanatory variables we choose to include.<\/p>\n A housing price model, for example, might use variables such as the number of rooms, median income, and so on. These factors explain part of the story\u2014but not always all of it.<\/p>\n Location matters too.<\/p>\n The neighborhood surrounding a property, the demographic profile of nearby communities, housing patterns, and environmental conditions can all influence the housing prices in ways that are difficult to capture individually.<\/p>\n Because the embeddings in USA Geodemographic Embeddings are a distillation of many aspects of geodemographic context into a simple vector of numbers, they can be used alongside existing predictors to enrich downstream models. In the housing price example shown below, adding embeddings to the original predictor set improved model performance compared to using the original variables alone.<\/p>\n The goal isn’t to replace existing variables; it’s to complement them with additional geographic context.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2975938,"id":2975938,"title":"Figure 3","filename":"EsriBlog2.png","filesize":759056,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/what-if-location-context-came-built-in-introducing-usa-geodemographic-embeddings\/esriblog2","alt":"Housing price predictions improved by adding USA Geodemographic Embeddings to existing predictors.","author":"430728","description":"","caption":"Housing Price prediction results using existing predictors (left) and existing predictors with embeddings (right). Notice the reduction in the number of points in darker shades of red (more than 20% prediction error) when the embeddings in USA Geodemographic Embeddings were added.","name":"esriblog2","status":"inherit","uploaded_to":2975935,"date":"2026-07-09 12:20:54","modified":"2026-07-09 12:21:08","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1862,"height":812,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2.png","medium-width":464,"medium-height":202,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2.png","medium_large-width":768,"medium_large-height":335,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2.png","large-width":1862,"large-height":812,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2-1536x670.png","1536x1536-width":1536,"1536x1536-height":670,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2.png","2048x2048-width":1862,"2048x2048-height":812,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2-826x360.png","card_image-width":826,"card_image-height":360,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog2.png","wide_image-width":1862,"wide_image-height":812}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":" You might often find use-cases in which there aren\u2019t any existing explanatory variables for the target you want to predict. The embeddings in USA Geodemographic Embeddings can be plugged in as the contextual predictors even then.<\/p>\n"},{"acf_fc_layout":"content","content":" Not every project begins with a similarity search workflow or a prediction. Sometimes the goal is simply to understand how places relate to one another.<\/p>\n Which communities share similar characteristics? Where do transitions occur across a region? Are there groups of locations that behave similarly despite being far apart geographically?<\/p>\n The embeddings in USA Geodemographic Embeddings can be used to answer these questions directly. Use them for finding clusters to help reveal patterns that may not be apparent when examining individual datasets separately.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2975939,"id":2975939,"title":"Figure 4","filename":"EsriBlog3.png","filesize":1544640,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/what-if-location-context-came-built-in-introducing-usa-geodemographic-embeddings\/esriblog3","alt":"Clustered map of locations with similar geodemographic and environmental characteristics across the U.S. East Coast.","author":"430728","description":"","caption":"Clustered map showing groups of locations with similar geodemographic and environmental characteristics across multiple regions on the East Coast of the contiguous United States.","name":"esriblog3","status":"inherit","uploaded_to":2975935,"date":"2026-07-09 12:22:00","modified":"2026-07-09 12:22:18","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1729,"height":851,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3.png","medium-width":464,"medium-height":228,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3.png","medium_large-width":768,"medium_large-height":378,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3.png","large-width":1729,"large-height":851,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3-1536x756.png","1536x1536-width":1536,"1536x1536-height":756,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3.png","2048x2048-width":1729,"2048x2048-height":851,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3-826x407.png","card_image-width":826,"card_image-height":407,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/07\/EsriBlog3.png","wide_image-width":1729,"wide_image-height":851}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":" By now, you must have learned one of the most interesting aspects of the embeddings in USA Geodemographic Embeddings\u2014that they are not tied to a single application.<\/p>\n The same layer can support similarity search, clustering, model enrichment, and other GeoAI workflows. That too, without assembling a new collection of geodemographic and environmental variables for every new project.<\/p>\n Behind the scenes, the embeddings are generated using Esri’s Geodemographic Foundation Model (GDFM)<\/a>. For most users, however, the important detail isn’t how the embeddings are created.<\/p>\n It’s what they enable.<\/p>\n They provide a new way to add context into analysis\u2014a way that is reusable, scalable, and ready to support the next generation of spatial analysis and GeoAI workflows.<\/p>\n"},{"acf_fc_layout":"content","content":" Like any contextual dataset, USA Geodemographic Embeddings works best when used thoughtfully.<\/p>\n A good starting point is to treat the embeddings as one single feature rather than a collection of individual variables. The information is distributed across all embedding dimensions, so they are most effective when used together.<\/p>\n The embeddings are expected to perform best in workflows in which geodemographic context matters.<\/p>\n For predictive workflows, embeddings don’t have to replace existing explanatory variables. As you have seen above, they can be used alongside domain-specific data to provide additional context and help enhance downstream analysis.<\/p>\n If you’re exploring the embeddings for the first time, consider starting with a similarity search or clustering workflow. These approaches provide an intuitive way to understand how locations relate to one another before moving on to more advanced modeling tasks.<\/p>\n"},{"acf_fc_layout":"content","content":" The USA Geodemographic Embeddings layer is available through ArcGIS Living Atlas of the World and can be accessed directly in ArcGIS Pro. The layer works with embedding-aware tools including Find Similar Features Using Embeddings<\/a>, Merge Embeddings<\/a>, and Extract Embeddings<\/a>, model development workflows such as Train Using AutoML<\/a>, and many other ArcGIS Pro tools, making it easy to incorporate them into existing projects.<\/p>\n We look forward to seeing how you use them for your workflows.<\/p>\n"},{"acf_fc_layout":"content","content":"Start with a place<\/strong><\/h2>\n"},{"acf_fc_layout":"content","content":"
Add context to your models<\/strong><\/h2>\n"},{"acf_fc_layout":"content","content":"
Explore patterns across places<\/strong><\/h2>\n"},{"acf_fc_layout":"content","content":"
A reusable layer for geographic context<\/strong><\/h2>\n"},{"acf_fc_layout":"content","content":"
Make the most out of the embeddings<\/strong><\/h2>\n"},{"acf_fc_layout":"content","content":"
Get started<\/strong><\/h2>\n"},{"acf_fc_layout":"content","content":"
Suggested Reads<\/strong><\/h2>\n"},{"acf_fc_layout":"content","content":"
\n