DoorDash uses causal inference to improve supply and demand forecast accuracy
DoorDash's forecasting models could not account for hard-to-measure macroeconomic and calendar factors such as tax refunds and daylight saving because these factors lack a direct feature measure and standard feature engineering fails to capture their heterogeneous, time-varying demand impact.
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 · Unmeasurable factor identified
The forecasting team identifies a temporary demand fluctuation source that has no direct feature measure and cannot be captured by standard feature engineering.
Tools used
difference-in-differencestime-series models
Outcome
Applying causal inference methods to preprocess demand series before time-series modeling produced a sizable improvement in out-of-sample forecast accuracy and a sizable reduction in acquisition costs.
What failed first
Standard feature engineering and one-hot encoding of concurrent events introduced multicollinearity that prevented disentangling individual factor impacts, and tax refund data alone could not capture the time-varying heterogeneous response across consumer segments, causing models to treat temporary spikes as permanent trends.
Results
Cost replacedsizable reduction in the Dx acquisition costs