DoorDash improves holiday supply and demand forecast accuracy with a cascade ML approach
DoorDash's supply and demand forecasting relied on tree-based ML models (GBM, Random Forest) that struggle to handle high variation during holidays because each holiday only appears once a year in training data, causing forecast accuracy to dip around rare extreme events and forcing ad-hoc manual interventions.
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 · Operational forecasting trigger
DoorDash generates supply and demand forecasts to proactively plan operations such as acquiring Dashers and adding extra pay when low supply is anticipated.
Tools used
GBMSpark
Outcome
The cascade approach reduced wMAPE over Christmas from between 60–70% to between 10–20%, achieved a 10% absolute wMAPE improvement averaged across all holidays, and backtests showed a ~25% reduction in volume lost from bad quality over Thanksgiving and Christmas.
What failed first
The GBM model's weighted mean absolute percentage error (wMAPE) deteriorated to between 60% and 70% around Christmas, as tree-based models averaged extreme holiday observations into a single final node rather than predicting each holiday accurately.
Results
Time saved10%
Volumedecreased from between 60% and 70% to between 10% and 20%