ecommerce_ops · ecommerce · workflow
DoorDash builds a GenAI-powered personalized homepage carousel system
DoorDash's original heuristic-based content system with around 300 curated carousels lacked sufficient concept diversity, produced overly broad and impersonal recommendations, and suffered from suboptimal knowledge graph tagging that matched stores to irrelevant carousels or omitted relevant ones.
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 · Consumer profile and day-part input
The pipeline takes a consumer profile and part of day as input to kick off personalized carousel generation.
Tools used
LLMsSpark
Outcome
The GenAI carousel system improved store retrieval precision@10 from 68% to 85%, delivered double-digit click rate improvement, and drove improving conversion rates and homepage relevance metrics.
Results
Volume68%
Grounding & classification
Source type: technical build writeup
25 fields verified against source quotes.
content generationpersonalizationrecommendation systemknowledge baseproduct catalogfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementconversion increasecustomer satisfactiontechnical build writeupecommerce opsextract classify route