DoorDash uses machine learning and SHAP values to discover online menu best practices and improve merchant conversion rates
Online menus lack the visual and experiential elements of physical storefronts, leaving the menu as the sole driver of customer conversion; unattractive or poorly organized menus can significantly hurt merchant sales, yet discovering which menu characteristics drive success at scale was difficult because most menu data is unstructured.
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 · Define menu feature set
Features were defined at each layer of menu design — overall appearance, category, item, and item options — to build model inputs across structure, customizability, and aesthetics.
ML models identified photo coverage, item customizability, and category mix as top conversion drivers; A/B experiments showed a hefty improvement from header photos and restaurant information; cuisine-specific model reruns revealed that optimal menu design varies significantly by restaurant type.
What failed first
Initial linear regression and base tree models had high error rates and feature collinearity issues; subsequent boosted models improved accuracy but created a black box explainability problem where the directional impact of individual features was unclear.