From Clicks to Conversions: Architecting Shopping Conversion Candidate Generation at Pinterest

Summary

Pinterest built a dedicated shopping candidate generation model to optimize for lower-funnel purchase conversions rather than relying strictly on engagement retrieval models. Because offsite conversion events are sparse and delayed, engineers trained a single multi-surface two-tower model using conversion data supplemented by duration-weighted click engagement and unengaged ad impressions as hard negatives. The two-tower retrieval architecture incorporates a parallel DCN v2 and MLP layer structure that allows simultaneous learning from the same inputs without information bottlenecks. Later revisions transitioned the system from a multi-head loss structure to a unified single-head multi-task architecture paired with an advertiser-level objective. Deployed across more than 600 million monthly active users, the system increased shopping conversion volume by 2.3% and boosted return on ad spend by 3.1% for United States shopping campaigns.

Takeaways

1. 1

   Replacing sequential DCN v2 and MLP cross layers with a parallel design yielded an 11% increase in offline recall@1000 by letting both networks learn directly from input features.

2. 2

   Transitioning to a unified single-head multi-task architecture with an advertiser-level loss function delivered a 42% average increase in recall@100 over the 2023 baseline model.

3. 3

   Deploying the conversion candidate generation system drove a 2.3% lift in shopping conversion volume, a 1.5% increase in CTR, and a 3.1% improvement in US shopping campaign RoAS.