logistics_ops · workflow
DoorDash upgrades store-closure heuristic with ML to save thousands of canceled orders weekly
DoorDash lacked accurate real-time merchant operational status, causing Dashers to arrive at physically closed stores. Human review of thousands of daily 'store closed' reports was too costly and slow to scale.
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 · Dasher reports store closed
When a Dasher finds a store location appears closed, they are prompted to upload a photo of the storefront to kick off the DRSC reporting process.
Tools used
LightGBM
Outcome
After deploying the ML model and validating through an A/B experiment, the improved decision-making saves thousands of deliveries from being canceled every week, producing better consumer experience, increased merchant revenue, and more Dasher earning opportunities.
What failed first
A heuristic rule-based approach to validating DRSC reports was only moderately accurate, and errors in passing inaccurate reports were costly to merchants and painful for customers.
Results
Time savedthousands of deliveries from being canceled every week
Grounding & classification
Source type: technical build writeup
19 fields verified against source quotes.
computer visionpredictive analyticsform submissionfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedlogisticsautomation ratecost reductionerror reductiontechnical build writeuplogistics opsorder processingextract classify routemonitor detect alert