home.social

#recommendationengine — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #recommendationengine, aggregated by home.social.

  1. New research shows a tuned recommendation engine can boost click‑through rates by 10% while cutting inference cost. The paper dives into model‑serving tricks, optimization for large language models, and deployment efficiency for production AI. Open‑source practitioners will love the practical benchmarks. #RecommendationEngine #InferenceOptimization #ModelServing #ClickThroughRate

    🔗 aidailypost.com/news/recommend

  2. New research shows a tuned recommendation engine can boost click‑through rates by 10% while cutting inference cost. The paper dives into model‑serving tricks, optimization for large language models, and deployment efficiency for production AI. Open‑source practitioners will love the practical benchmarks. #RecommendationEngine #InferenceOptimization #ModelServing #ClickThroughRate

    🔗 aidailypost.com/news/recommend

  3. New research shows a tuned recommendation engine can boost click‑through rates by 10% while cutting inference cost. The paper dives into model‑serving tricks, optimization for large language models, and deployment efficiency for production AI. Open‑source practitioners will love the practical benchmarks. #RecommendationEngine #InferenceOptimization #ModelServing #ClickThroughRate

    🔗 aidailypost.com/news/recommend

  4. Data Annotation for Smarter AI & Recommendations in E-commerce

    Discover how quality data annotation empowers e-commerce businesses to train smarter AI systems and recommendation engines. From image and text labeling to scalable automation, learn how accurate datasets drive personalization, better search, and higher engagement in online retail.

    #DataAnnotation #EcommerceAI #RecommendationEngine #AIDrivenRetail #MachineLearning #DataLabeling #PersonalizedShopping

  5. CW: Twitter

    It isn't clear to me whether an LLM is replacing Twitter's current recommendation-engine (i.e., what some misleadingly call "an algorithm" or "the algorithm") with an LLM.

    Or, if the LLM is more of a front-end to a non-LLM based recommendation-engine.

    RE: twitter.com/elonmusk/status/19

    #Grok #LLM #RecommendationEngine #Twitter

  6. RE: mastodon.social/@cheeaun/11538

    This is an argument for (also) having a recommendation-engine based feed.

    (I.e., what some mistakenly call "the algorithm" or an "algorithmic feed".)

    “I know the comparison here is 450 followers to 4,500, but follower number isn't indicative of the full picture. Think about TikTok, and how you can have 50 followers but have posts that reach millions of views.”

    RE: cara.app/post/2e0d29d3-a57a-4b

    #FediUX #Fediverse #FediverseUX #RecommendationEngine

  7. AI recommendation engines often fail due to poor data quality, lack of personalization, and algorithmic biases. Learn how to build smarter AI-driven recommendation systems with advanced machine learning techniques and optimized data strategies. Improve accuracy, relevance, and user engagement.

    Read more at amplework.com/blog/why-ai-reco

    #ai #recommendationengine #machinelearning #artificialintelligence

  8. Regarding:
    “Instagram will soon let you reset your recommendation algorithm”

    I am glad they called it a “RECOMMENDATION ENGINE” rather than “THE ALGORITHM”.

    The whole talk about “The Algorithm” is at best misleading — and probably actually harmful.

    [1] mastodon.social/@reiver/109431

    [2] mastodon.social/@reiver/110475

    [3] mastodon.social/@reiver/113406

    RE: mstdn.social/@TechCrunch/11350

    #algorithm #instagram #RecommendationEngine #TheAlgorithm

  9. The home feed of #Meta 's / #Facebook 's / #Instagram 's new social-media network #Threads seems to only be showing me posts from accounts I do NOT follow.

    I wonder if it is because the accounts I do follow there aren't posting (or aren't posting enough).

    Or their #RecommendationEngine (which so many people wrongly call the #Algorithm ) doesn't seem good at figuring out what I'm interested in. Maybe it doesn't have enough data — although they do have data on me from Instagram.
    #project92 #p92

  10. #SocialMedia #Twitter #Algorithms #RecommendationEngine: "To me, the most important thing that Twitter revealed is the formula that specifies how different types of engagement (likes, retweets, replies, etc.) are weighed relative to each other. 2. I’ve focused on the “heavy ranker” step of the sourcing and ranking pipeline under the assumption that it has the biggest effect on the overall algorithm.I’ll discuss the formula itself in a second. But first, I want to note that the formula isn’t actually in the code! That’s because it needs to be tweaked frequently and so is stored separately from the code, which is relatively static. Twitter had to separately publish it. This again shows the limits of code transparency.

    The code does reveal one important fact, which is that Twitter Blue subscribers get a boost in reach—although, again, Twitter could have simply announced this instead of burying it in the code. (The Twitter Blue webpage does advertise that replies by Blue users are prioritized, but doesn’t mention the boost for regular tweets, which seems much more significant.)"

    knightcolumbia.org/blog/twitte

  11. #SocialMedia #Twitter #Algorithms #RecommendationEngine: "Twitter aims to deliver you the best of what’s happening in the world right now. This requires a recommendation algorithm to distill the roughly 500 million Tweets posted daily down to a handful of top Tweets that ultimately show up on your device’s For You timeline. This blog is an introduction to how the algorithm selects Tweets for your timeline.

    Our recommendation system is composed of many interconnected services and jobs, which we will detail in this post. While there are many areas of the app where Tweets are recommended—Search, Explore, Ads—this post will focus on the home timeline’s For You feed."
    blog.twitter.com/engineering/e