TLDR Tech / Data
From Clicks to Conversions: Architecting Shopping Conversion Candidate Generation at Pinterest
Pinterest built a dedicated two-tower retrieval model to generate better shopping ad candidates optimized for offsite conversions, moving beyond traditional click/engagement-based signals which are abundant but poorly correlated with actual buying intent. The system uses a unified multi-task architecture with parallel DCN v2 and MLP cross layers, clever training techniques to handle sparse and noisy conversion data, and an advertiser-level loss function.
Read the full story