Making User-Sequence Data More Cost-Efficient, Faster, and Easier to Use

2026-05-22

Pinterest redesigned its machine learning data platform to use a single configuration-as-code definition that standardizes user-sequence data across real-time indexing, batch processing, and online serving. This lambda-style architecture and columnar, time-partitioned storage model reduced infrastructure costs while speeding up the onboarding of new events and enrichments.