Company

Pinterest

47 cases from Pinterest (Social, Adtech, E-commerce), each digested from a public talk or engineering post and linked to the original. 28 were checked in an online A/B test; 16 report results in production.

Tasks: Retrieve and rank from millions of items, Reduce ML cost, Recommend from what the user just did, Balance relevance and diversity, Evaluate models and 18 more. Methods: Multi-task learning, Two-tower model, Deep & Cross Network, Knowledge distillation, Two-stage recommender, Sequential recommendation and 80 more. Tools: PyTorch, Apache Airflow, Apache Spark, Ray, Qwen, Apache Iceberg and 24 more.

Tech blog: medium.com/@Pinterest_Engineering

How Pinterest Improved Analytics Agent Compliance with Loop Engineeringsocial2026-11
Safe and Efficient Multi-Epoch Embedding Trainingsocial2026-11
From Activity to Intent: Generating User Journeys with LLMssocial2026-10
Metrics Board: Building an Agent-ready Metrics Layersocial2026-10
Beyond Two Towers: Launching the 3-Tower Engagement Co-Train Model (Part 2)adtech2026-09
Pinner Progression: Better Use-Case Representation Driving Weekly Active User Growth at Pinterestsocial2026-07
Enhancing Ad Relevance: Integrating Real-Time Context into Sequential Recommender Modelsadtech2026-05
From Clicks to Conversions: Architecting Shopping Conversion Candidate Generation at Pinterestadtech2026-04
Evolution of Multi-Objective Optimization at Pinterest Home feedsocial2026-04
Scaling Recommendation Systems with Request-Level Deduplicationsocial2026-04
Unifying Ads Engagement Modeling Across Pinterest Surfacesadtech2026-03
Unified Context-Intent Embeddings for Scalable Text-to-SQLsocial2026-03
GPU-Serving Two-Tower Models for Lightweight Ads Engagement Predictionadtech2026-02
Ads Candidate Generation using Behavioral Sequence Modelingsocial2026-01
PinLanding: Turn Billions of Products into Instant Shopping Collections with Multimodal AIe-commerce2026-01
LLM-Powered Relevance Assessment for Pinterest Searchsocial2025-12
How Pinterest Built a Real‑Time Radar for Violative Content using AIsocial2025-12
Improving Quality of Recommended Content through Pinner Surveyssocial2025-12
Identify User Journeys at Pinterestsocial2025-10
Unlocking Efficient Ad Retrieval: Offline Approximate Nearest Neighbors in Pinterest Adsadtech2025-06
Next-Level Personalization: How 16k+ Lifelong User Actions Supercharge Pinterest’s Recommendationssocial2025-06
Modernizing Home Feed Pre-Ranking Stagesocial2025-05
How Pinterest Accelerates ML Feature Iterations via Effective Backfillsocial2025-05
500X Scalability of Experiment Metric Computing with Unified Dynamic Frameworksocial2025-05
Multi-gate-Mixture-of-Experts (MMoE) model architecture and knowledge distillation in Ads Engagement modeling developmentadtech2025-04
Improving Pinterest Search Relevance Using Large Language Modelssocial2025-04
Module Relevance on Home Feedsocial2025-03
The Quest to Understand Metric Movementssocial2025-02
Advancements in Embedding-Based Retrieval at Pinterest Homefeedsocial2025-02
Establishing a Large Scale Learned Retrieval System at Pinterestsocial2025-01
NEP: Notification System and Relevancesocial2024-08
How we built Text-to-SQL at Pinterestsocial2024-04
The Field Guide to Non-Engagement Signalssocial2024-03
LinkSage: GNN-based Pinterest Off-site Content Understandingsocial2024-03
User Action Sequence Modeling for Pinterest Ads Engagement Modelingadtech2024-03
Handling Online-Offline Discrepancy in Pinterest Ads Ranking Systemadtech2024-01
Evolution of Ads Conversion Optimization Models at Pinterestadtech2024-01
Training Foundation Improvements for Closeup Recommendation Rankersocial2023-09
Building for Inclusivity: The Technical Blueprint of Pinterest’s Multidimensional Diversificationsocial2023-09
Deep Multi-task Learning and Real-time Personalization for Closeup Recommendationssocial2023-06
Representation online matters: practical end-to-end diversification in search and recommender systemssocial2023-05
Warden: Real Time Anomaly Detection at Pinterestsocial2023-05
An ML based approach to proactive advertiser churn preventionadtech2023-05
How Pinterest Leverages Realtime User Actions in Recommendation to Boost Homefeed Engagement Volumesocial2022-11
Query Rewards: Building a Recommendation Feedback Loop During Query Selectionsocial2022-10
Estimating Potential Audience Size of an Ad at Pinterestadtech2022-06
Experiment without the wait: Speeding up the iteration cycle with Offline Replay Experimentationsocial2022-01