PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest
2026-07-24 • Information Retrieval
Information RetrievalMachine Learning
AI summaryⓘ
The authors present a new method to help search and recommendation systems show new content more effectively. Their approach works well across different stages of how content is discovered and can be used for both searching and recommending items. It also reduces bias towards popular or existing content, allowing fresher content a better chance to be seen. They tested their system at Pinterest and found it improved how much new content users explored, increased user engagement, and supported a healthier content environment overall.
content cold-startsearch systemsrecommender systemsmulti-stage funnelcontent biasuser engagementcontent explorationexperimental evaluationPinterestcontent ecosystem
Authors
Olafur Gudmundsson, Bo Zhao, Huayi Liao, Anna Kiyantseva, Sai Xiao, Heath Vinicombe, Mostafa Keikha, Luke DeLuccia, Zihao Chen, Junpeng Hou, Weijie Jiang, Bhawna Juneja, Andreanne Lemay, Wei-Ting Lin, Keyvan Moghadam, Jiaxing Qu, Zhiqing Rao, Zhihua Zhang
Abstract
In this paper, we propose a new solution for addressing the content cold-start problem in industry-scale search and recommender systems. Compared to prior approaches, we have made the following new contributions: 1) our solution spans the entire multi-stage funnel and generalizes well for both search and recommendation surfaces, 2) our solution reduces bias favoring existing content, allowing more accurate model prediction across content types and reducing short-term tradeoffs associated with high volumes of explicit content exploration, 3) our solution is evaluated with a scalable measurement framework that enables fast short-term experimentation while validating long-term impact. We have iteratively built and successfully deployed this new system at Pinterest in the past two years and observed significant improvements in fresh content exploration, overall user engagement, and content ecosystem health.