T-REX Articles

  • diagram-showing-the-architecture-of-identity-services

    How we reduced latency and cost-to-serve by merging two systems

    April 22, 2020

    Co-authors: Xiang Zhang, Estella Pham, and Ke Wu Identity services are critical systems that serve data on profile and member settings to help power many other applications at LinkedIn. In this blog post, we’ll share how we merged two layers of the identity services that handle more than half a million queries per second (QPS) that drove a 10% reduction in...

  • metadata-library-updates

    Rapid experimentation through standardization: Typed AI features for LinkedIn’s feed

    April 15, 2020

    Serving the most relevant information for LinkedIn members in the homepage feed requires a massive effort—hundreds of features are used to personalize content for hundreds of millions of members. For each homepage visit, our machine learning models have to find and surface the best activity across a member's whole network, and they have to source that content...

  • building-inclusive-products-through-a-b-testing

    Building inclusive products through A/B testing

    March 31, 2020

    Co-authors: Guillaume Saint-Jacques, Amir Sepehri, Nicole Li, and Igor Perisic Introduction Previously on this blog, we’ve shared information on best practices in data science, particularly in areas such as A/B testing. We’ve also discussed the importance of ethics in fields such as data science, early implementations of “fairness by design” principles in our...

  • diagram-of-linkedin-services-and-the-lix-engine

    Making the LinkedIn experimentation engine 20x faster

    January 3, 2020

    Co-authors: Alexander Ivaniuk, Jingbang Liu At LinkedIn, we like to say that experimentation is in our blood because no production...

  • results-graph-image

    Understanding network quality: The rise of customized...

    June 10, 2019

    “Make LinkedIn feel instantaneous” is a mantra our performance team lives by to deliver the best possible experience to our members....

  • cluster-illustration

    Detecting interference: An A/B test of A/B tests

    June 5, 2019

    At LinkedIn, most decisions are made using experiments. When we want to decide between two features, we test them against each other...