United StatesLogistics and transport2023 – ongoingDoorDash
Sift machine-learning payment fraud detection
Sift reported that DoorDash increased fraud-review efficiency 2x-3x
Problem
Fraudsters bought deliveries with stolen cards, leaving DoorDash with disputed charges. Manual reviews and frequently revised fraud rules consumed the risk team's time.
Approach
DoorDash adopted Sift Payment Protection rather than building its own tool. The team examined links between accounts and automated the labeling and blocking of suspicious users associated with chargebacks. Machine learning used fraudulent behavior to recognize similar activity.
Results
Takeaway
The team combined model-based detection with configurable review workflows. Sift did not disclose the measurement period behind its efficiency claim.
Categories
- Size
- Large enterprise
- Industry
- Logistics and transport
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Vendor case study
Sources
Source summaries
Sift described how DoorDash combined shared fraud signals with automated account-handling workflows. It reported 2x-3x higher review efficiency and daily avoided fraud losses measured in thousands of dollars.
Full details are in the original sources.
