ecommerce_ops · ecommerce · workflow

DoorDash uses LLMs to bridge behavioral silos in multi-vertical recommendations

As DoorDash expands into more verticals, most customers have deep behavioral history in only a few categories — especially restaurants — leaving them effectively cold-start in grocery, retail, and convenience. Standard recommenders have little per-SKU signal, and popularity baselines overexpose head products while pushing aside long-tail items, weakening personalization across large, sparse catalogs.

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 · User behavior data as input
Unstructured user behavior — restaurant orders and search queries — serves as input to the LLM feature pipeline.
Tools used
LLMGPT 4oGPT 4o-miniH-RAG
Outcome

The LLM-powered framework achieved a 4.4% relative improvement in AUC-ROC and 4.8% improvement in MRR offline, confirmed with +4.3% AUC-ROC and +3.2% MRR gains in online production, while cutting total computation costs by ~80%.

What failed first

Before prompt refinements, the LLM assigned overly generic and incorrect category tags — a user who ordered Indian food was tagged with categories like 'Sandwiches' rather than relevant fine-grained categories like 'Specialty Breads (Naan)'.

Results
Volume4.4%
Cost replaced~80%
Source

https://careersatdoordash.com/blog/doordash-llms-bridge-behavioral-silos-in-multi-vertical-recommendations/

How we source this →

Grounding & classification
Source type: technical build writeup
33 fields verified against source quotes.
data extractionpersonalizationragrecommendation systemknowledge baseproduct catalogfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedecommerceaccuracy improvementcost reductiontechnical build writeupecommerce opsdata sync enrichmentextract classify route