--- title: Innovative Recommendation Applications Using Two Tower... description: Uber has developed Two-Tower Embeddings (TTE) for its recommendation systems, using embeddings to improve scalability and efficiency. TTE provides personalized... canonical: https://daily.dev/posts/innovative-recommendation-applications-using-two-tower-embeddings-at-uber-3uiow1ns8 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Innovative Recommendation Applications Using Two Tower Embeddings at Uber | daily.dev og:description: Uber has developed Two-Tower Embeddings (TTE) for its recommendation systems, using embeddings to improve scalability and efficiency. TTE provides personalized... og:url: https://daily.dev/posts/innovative-recommendation-applications-using-two-tower-embeddings-at-uber-3uiow1ns8 og:image: https://api.daily.dev/og/posts/3UioW1NS8.png og:image:alt: Innovative Recommendation Applications Using Two Tower Embeddings at Uber og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Innovative Recommendation Applications Using Two Tower Embeddings at Uber **[Community Picks](https://daily.dev/sources/community)** · 14 min read · 5 upvotes · 0 comments ## Summary Uber has developed Two-Tower Embeddings (TTE) for its recommendation systems, using embeddings to improve scalability and efficiency. TTE provides personalized retrieval from a large pool of stores and can be used for final ranking in recommendation systems. The TTE model utilizes engagement data and localized relations to optimize training and inference. It offers feature extensibility and has been successful in improving performance and lowering costs at Uber. Challenges include model size, training time, and evaluation metrics. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#ai](https://daily.dev/tags/ai), [#embeddings](https://daily.dev/tags/embeddings), [#machine-learning](https://daily.dev/tags/machine-learning), [#recommendation-systems](https://daily.dev/tags/recommendation-systems) [View this post on daily.dev](https://daily.dev/posts/innovative-recommendation-applications-using-two-tower-embeddings-at-uber-3uiow1ns8) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Innovative Recommendation Applications Using Two Tower Embeddings at Uber","url":"https://daily.dev/posts/innovative-recommendation-applications-using-two-tower-embeddings-at-uber-3uiow1ns8","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/innovative-recommendation-applications-using-two-tower-embeddings-at-uber-3uiow1ns8"},"datePublished":"2024-05-02T05:16:11.331Z","dateModified":"2024-07-02T02:14:57.536Z","description":"Uber has developed Two-Tower Embeddings (TTE) for its recommendation systems, using embeddings to improve scalability and efficiency. TTE provides personalized...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6a93ddbf8383f7f92ac77025e72601f6?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6a93ddbf8383f7f92ac77025e72601f6?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"Community Picks","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Community Picks","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1655817725/logos/community","url":"https://daily.dev/sources/community"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/innovative-recommendation-applications-using-two-tower-embeddings-at-uber-3uiow1ns8","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":5},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,embeddings,machine-learning,recommendation-systems","timeRequired":"PT14M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Community Picks","item":"https://daily.dev/sources/community"},{"@type":"ListItem","position":3,"name":"Innovative Recommendation Applications Using Two Tower Embeddings at Uber"}]} ```