How Pinterest Uses Machine Learning

The article discusses the implementation of a GPU-serving two-tower model for lightweight ads engagement prediction at Pinterest.

This article discusses the re-architecture of the serving stack for next-generation ads lightweight ranking models at Pinterest, moving from a traditional Two-Tower architecture to a more complex G...

The article discusses how Pinterest enhances its ad candidate generation process using behavioral sequence modeling.

PinLanding is a multimodal AI pipeline developed by Pinterest to generate shopping collections from billions of products.

The article discusses the implementation of LLM-powered relevance assessment at Pinterest Search, focusing on how fine-tuned large language models (LLMs) can enhance search relevance measurement wh...

The article discusses how Pinterest utilizes Pinner surveys to enhance the quality of recommended content on its platform.

The article discusses Pinterest's strategic shift towards prioritizing open-source AI models over proprietary ones, highlighting the cost-effectiveness and performance benefits of fine-tuning open-...

The article discusses how Pinterest identifies user journeys to enhance its recommendation system, moving beyond immediate interests to understand users' long-term goals.

This article discusses how Pinterest enhances its recommendation system through the TransActV2 model, which leverages over 16,000 lifelong user actions to improve personalization.

The article discusses the modernization of Pinterest's home feed pre-ranking stage, focusing on the introduction of a sophisticated pre-ranking layer known as Lightweight Scoring.

The article discusses the Multi-gate Mixture-of-Experts (MMoE) model architecture and the application of knowledge distillation in enhancing Ads Engagement modeling.

The article discusses the implementation of a Large Language Model (LLM)-based relevance system for Pinterest Search, detailing its technical design, model architecture, and the results from both o...

The article discusses advancements in embedding-based retrieval at Pinterest's Homefeed, focusing on improvements such as feature crossing, ID embeddings, and serving corpus upgrades.

The article discusses the establishment of a large-scale learned retrieval system at Pinterest, focusing on the transition from heuristic-based methods to an embedding-based retrieval system.

The article highlights Pinterest's Mentors of the Year for their internship program, showcasing the personal and professional growth experienced by both mentors and interns.

This article discusses the redesign of Pinterest's ad serving systems, focusing on achieving zero downtime during the transition.

The article discusses the Notification Event Processor (NEP) developed at Pinterest, which enhances user engagement through a flexible, real-time notification system.

This article discusses the complete redesign of Pinterest's ad serving system, known as Mohawk, which was rewritten to eliminate technical debt and improve performance, enabling the company to meet...

LinkSage is a Graph Neural Network-based model developed by Pinterest to enhance off-site content understanding, improving user engagement and monetization.

The article discusses the implementation of user action sequence modeling at Pinterest to enhance ad engagement through personalized recommendations.

The article discusses the challenges of online-offline discrepancies in Pinterest's ads ranking system, emphasizing the importance of aligning offline model performance with online business metrics.

The article discusses the evolution of ads conversion optimization models at Pinterest, highlighting the transition from Gradient Boosted Decision Trees (GBDT) to advanced Deep Neural Networks (DNN...

Makeathon 2023 is Pinterest's annual internal hackathon where employees collaborate to develop innovative projects aimed at enhancing the company's products and culture.

The article discusses Pinterest's commitment to inclusivity through its technical advancements in machine learning, particularly focusing on body type representation alongside existing skin tone si...

The article discusses how Pinterest improved its machine learning (ML) dataset iteration speed using Ray, an open-source framework for scaling AI and ML workloads.

The article features an interview with Behnam Rezaei, Pinterest's VP of Engineering, discussing the unique aspects of working in the Monetization Engineering team.

The article discusses the importance of representation in search and recommender systems, specifically focusing on how Pinterest has implemented end-to-end diversification techniques to improve use...

This article discusses a Machine Learning (ML) based approach to proactively prevent advertiser churn at Pinterest.

The article discusses how Pinterest utilizes machine learning to maintain a positive comment ecosystem amidst a growing creator community.

The article discusses the Campaign Budget Optimization (CBO) product developed by Pinterest's Ads Intelligence team, which automates the distribution of advertising budgets across ad groups to maxi...

The article discusses the Advertiser Recommendation Systems developed by the Ads Intelligence team at Pinterest, focusing on how machine learning and algorithms are utilized to enhance the advertis...

The article discusses how Pinterest utilizes Apache Spark SQL for interactive querying, detailing the architecture, challenges faced, and solutions implemented to enhance user experience.

The article discusses how Pinterest employs machine learning to combat spam and harmful content on its platform.

The article discusses how Pinterest employs machine learning to combat misinformation, hate speech, and self-harm content on its platform.

The article profiles Rahim Daya, the Head of International Product and Toronto Lead at Pinterest, highlighting his career journey and the company's expansion efforts in Toronto.

The article discusses the implementation of a multi-task learning model for recommending related products on Pinterest, focusing on improving engagement metrics through a more flexible and interpre...

This article discusses the transition from a single-output deep neural network to a multi-task learning (MTL) framework for home feed ranking at Pinterest.

The article discusses how Pinterest empowered its data scientists and machine learning engineers by building a PySpark infrastructure that addresses challenges faced with existing tools like Hive a...

This article discusses the importance of annotations in Pinterest's visual discovery engine, focusing on how these keywords help in understanding text associated with Pins.

The article discusses the technological framework that supports Pinterest's growth, detailing the company's mission to help users discover and do things they love.