DoorDash reimagines hyper-personalization by layering LLMs over classic ML systems
Classic personalization systems built on collaborative filtering, embeddings, and deep learning could not meet customers at their moment of need or incorporate world knowledge about new inventory, while human-centric product-attribute extraction and editorial merchandising could not scale to millions of individual consumers.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · LLM product attribute extraction
LLMs extract product attributes such as noise-canceling status, brand, color, and form factor from item listings.
Tools used
LLMsRAGDSPyGEPAMTML
Outcome
DoorDash reduced a product-attribute extraction task from 28 days to 2 days using LLMs with fine-tuning, RAG, and agentic processes, and built a hyper-personalization system that generates per-consumer carousel blueprints offline and blends real-time intent signals online to serve moment-aware, individualized experiences.
What failed first
Static personalization approaches — including matrix factorization, LDA, wide-plus-deep models, and two-tower embeddings — learned only from long-term in-app engagement and could not react fast enough to short-lived, high-context moments like Black Friday or new merchant inventory with no engagement history.