Pinterest develops model-agnostic framework for long-term user engagement

Researchers at Pinterest have developed a new model-agnostic framework designed to optimize long-term user engagement and retention in large-scale recommendation systems. This framework addresses the challenges of sparse, delayed, and partially attributable return signals by identifying session-level behaviors that predict future retention. The system has been successfully deployed across various Pinterest surfaces, including Homefeed, Related Pins, Search, and Notifications, demonstrating consistent improvements in engagement and retention metrics. AI

IMPACT Enhances long-term user retention in recommendation systems, potentially influencing future recommender system design.

RANK_REASON Academic paper detailing a new framework for recommendation systems. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• arXiv
• CORE Recommender
• Dingsu Wang
• Homefeed
• IArxiv Recommender
• Notifications
• Pinterest
• Related Pins
• Search

• product
• paper

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →