DoorDash NextGen ETA system: multi-task deep learning with probabilistic forecasts
DoorDash's ETA prediction required a cumbersome array of specialized tree-based models, one per delivery type, which became unsustainable to maintain and reached a performance plateau where additional data, features, and enhancements yielded no further improvement. Separately trained models also produced ETA discrepancies across consumer touchpoints, harming the customer experience.
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 · Customer ETA request
A customer at the home page, store page, or checkout triggers an ETA prediction request.
Tools used
Deep Learningneural networksmulti-task
Outcome
DoorDash developed three versions of NextGen ETA models that improve consumer outcomes on accuracy and consistency, with multi-task learning notably improving predictions for lower-volume markets such as Australia.
What failed first
Tree-based models could not generalize to unseen or rare delivery scenarios and forced accuracy tradeoffs between earliness and lateness rather than improving overall on-time prediction.