Pinterest uses an AI system to classify each user's active interests into named 'journeys,' such as planning a nursery or exploring Japanese cuisine, and applies those journey labels to personalize the timing and content of email and push notifications. The system was described in an October 2025 Pinterest Engineering blog post. In initial experiments covering April-May 2025, journey-aware notifications produced an 88% higher email click rate and a 32% higher push open rate compared to the prior interest-based notification system.

The system extracts keywords from a user's recent searches, saves, and boards, then uses hierarchical clustering to group those keywords into journey candidates, which are then named, ranked, and classified by stage. Pinterest used GPT to generate ground-truth labels for fine-tuning Qwen, a smaller open-source model, so that journey classification could run at scale with lower cost and latency. The journey labels are matched to relevant Pin content and used to personalize email and push notification timing and content. Pinterest also uses an LLM-based evaluation pipeline to score the relevance of predicted journeys, which the engineering team reports correlates closely with human assessments.