How LinkedIn Uses Machine Learning

The article discusses LinkedIn's approach to matching its members with the appropriate Premium products using a unified machine learning platform.

The article discusses the open sourcing of FlyteInteractive, a tool developed by LinkedIn to enhance machine learning (ML) development productivity.

The article discusses LinkedIn's journey in evolving its professional community policies enforcement at scale, focusing on the development of its anti-abuse platform and account restriction systems.

The article discusses how LinkedIn enhances its content review processes by leveraging Automated Machine Learning (AutoML) to proactively address threats and improve content moderation systems.

The article discusses how LinkedIn enhances its content moderation efforts through a new framework that utilizes machine learning for dynamic content prioritization.

The article explores Javier's transition from a music career to data science, highlighting the intersection of math and music in his journey.

The article introduces OpenHouse, a control plane developed at LinkedIn for managing tables in open source data lakehouse deployments.

The article discusses new techniques developed by LinkedIn's Trust Data Team in collaboration with academia to detect AI-generated profile photos.

The article discusses the development and maintenance of LinkedIn's skills taxonomy, which underpins the Skills Graph.

The article discusses the development of LinkedIn's Skills Graph, which aims to create a skills-first job market by mapping the relationships between skills, people, and organizations.

The article discusses the implementation of render models at LinkedIn, which centralizes business logic on the server to enhance the efficiency and consistency of client applications.

The article discusses the challenges and practical lessons learned from building a deep-learning-based click-through rate (CTR) prediction model for LinkedIn ads.

The article discusses the limitations of last-click attribution in marketing and introduces the Bayesian Structural Time Series (BSTS) model as a solution for measuring the incremental impacts of m...

The article discusses LinkedIn's MLOps portal, Pro-ML Workspace, which was launched to enhance the productivity of machine learning engineers by providing a structured approach to manage the full l...

The article discusses the open sourcing of Feathr, LinkedIn's feature store designed to simplify machine learning feature management and enhance developer productivity.

The article introduces FastTreeSHAP, an open-source Python package designed to accelerate SHAP value computations for tree-based models.

The article discusses the Performance-Adaptive Sampling Strategy (PASS) for Graph Neural Networks (GNNs) and announces its open-source release.

The article discusses the completion of member knowledge graphs using Graph Neural Networks (GNNs), specifically introducing a novel model called Entity-BERT.

The article discusses the use of deep learning techniques to detect abusive sequences of member activity on LinkedIn.

The article discusses the Lambda Learner, a system designed for nearline learning on data streams, particularly for predicting click-through rates for Sponsored Content on LinkedIn.

The article discusses the optimization of the People You May Know (PYMK) recommendation system on LinkedIn to enhance equity in network creation.

The article discusses the implementation of multi-task learning for homepage feed ranking at LinkedIn using TensorFlow.

The article discusses LinkedIn's commitment to Responsible AI, outlining its principles and practices that prioritize member trust and safety.

The article introduces Greykite, an open-source Python library designed for fast and accurate time series forecasting.

The article discusses the innovative approach taken by LinkedIn to enhance site capacity projections using the Capacity Analyzer.

The article discusses the Smart Argument Suite, a Python library designed to streamline the process of passing command-line arguments for AI workflows.

The article discusses the LinkedIn Fairness Toolkit (LiFT), an open-source library designed to address bias in AI applications at scale.

The article discusses LinkedIn's approach to combating harassment on its platform, focusing on the use of technology and human expertise to create a safer environment for its users.

This article delves into the AI mechanisms behind course recommendations on LinkedIn Learning, focusing on the Deep Neural Network-based Collaborative Filtering approach and the Response Prediction...

The article discusses the open-sourcing of LinkedIn's Spark inequality A/B testing library, named spark-inequality-impact, aimed at measuring and reducing inequality in product design.

The article discusses Spark-TFRecord, a new data source for Apache Spark that aims to provide full support for the TFRecord data format used in TensorFlow.

The article discusses the implementation of typed AI features in LinkedIn's feed, emphasizing the importance of standardization for rapid experimentation and continuous improvement.

The article discusses how LinkedIn integrates A/B testing with concepts of economic inequality to build more inclusive products.

The article discusses LinkedIn's efforts to maintain a professional environment by detecting and removing inappropriate profiles using advanced machine learning techniques.

The article highlights the top ten engineering blogs from LinkedIn in 2019, focusing on popular topics such as open source, artificial intelligence, and technical challenges at scale.

The article discusses the implementation of the Isolation Forest algorithm by LinkedIn's Anti-Abuse AI Team to detect and prevent various types of abuse on the platform.

The article discusses how LinkedIn leverages data science and machine learning to drive business decisions, focusing on the importance of defining KPIs, conducting A/B testing, and following a stru...

The article discusses the AI-driven search and recommendation systems behind LinkedIn Recruiter, highlighting the unique challenges in talent search, the methodologies employed, and the system arch...

Avro2TF is an open-source feature transformation engine designed to facilitate the conversion of data into a format compatible with TensorFlow.

The article discusses the trends in artificial intelligence observed at the NeurIPS 2018 conference, highlighting the diversification of research topics, keynotes on public policy and reproducibili...

The article discusses LinkedIn's initiative to scale machine learning productivity through the Pro-ML program, which aims to enhance the effectiveness of machine learning engineers and democratize ...

The article discusses how LinkedIn utilizes Economic Graph data to enhance its Salary product, allowing users to access comprehensive compensation insights.

The article recaps the LinkedIn NYC Tech Talk Series focused on Machine Learning and Data Science, featuring presentations from experts at LinkedIn, Cornell Medicine, and Google.

The article discusses LinkedIn's automated systems for detecting fake accounts to maintain a safe professional community.

The article discusses the open sourcing of TonY, a framework designed to enable native support for TensorFlow on Hadoop.

The article discusses the Resume Assistant, a tool developed through the collaboration between Microsoft and LinkedIn, aimed at helping users create better resumes by leveraging AI to find high-qua...

The article discusses the integration of LinkedIn's Universal Content Filtering (UCF) platform with Microsoft's Content Moderator service to enhance the detection of inappropriate content on Linked...

The article discusses the implementation of dynamic machine translation in the LinkedIn feed, addressing the challenges of language barriers among users.

The article discusses the essential elements of modern data science, particularly in the context of Big Data and AI.

The article discusses the statistical modeling system that powers LinkedIn Salary, focusing on how it collects and processes compensation data while addressing privacy concerns.