Overview

Connecting people through delivery

DoorDash is a technology company that enables merchants to reach consumers via delivery. Dashers (delivery people) have the freedom and flexibility to work when they want, while restaurants are empowered to reach a greater pool of customers. Operating in the US, Canada, and Australia, DoorDash has both a desktop site and a mobile app, with most traffic coming through the iOS app.

Challenge

Exploiting the app for fraud

DoorDash had to contend with fraudsters that were using stolen credit cards and reselling DoorDash as a service illegally. They would advertise online through various platforms, claiming to be selling DoorDash at a significant discount and convincing consumers to make purchases through them. Consumers would provide their order details to the fraudster, who would then place the order using the stolen credit card, and the consumer would wire money to the fraudster. This left DoorDash in a position of having to reimburse the victim (either directly or via chargeback) whose credit card was stolen after the victim disputed the charge.

DoorDash was also experiencing chargebacks due to the charges on those stolen credit cards, and their rules-based fraud prevention needed to be regularly updated to stave them off, consuming time and resources.

In these early days of DoorDash, no automation was in place and most fraud prevention was done via manual review. DoorDash needed a solution that could proactively detect and prevent these fraudsters before they could make it onto the platform to do damage.

Solution

Proactively putting a stop to bad actors

Without enough manpower or bandwidth to build a fraud prevention tool internally, DoorDash’s Risk team turned to Sift’s Payment Protection product to ensure the integrity of their community. DoorDash chose Sift over other fraud prevention vendors because of the sheer amount of customers Sift works with across a number of industries. Following integration, DoorDash started to see significant, impactful results.

Using the Network view, DoorDash’s Risk team can see how many users on the platform are connected, enabling quick identification and removal of colluding fraudsters or fraudsters using multiple accounts. And on the Analyze page, they’re regularly reviewing their fraud-fighting strategy, testing their existing rules, and making new ones by leveraging the analytics available on the page.

Via Workflows, the team automated the labeling of fraudulent-looking users who initiate chargebacks (used in tandem with information they receive from their third-party payments processor). The user is prevented from returning to the platform, and the machine learning model recognizes that fraudulent behavior in other users. 

The wealth of data that DoorDash has available to them in being part of Sift’s global network has been invaluable to the Risk team for not only identifying fraud but recognizing the behaviors of good users, as well. If a signal is flagged as potentially risky, the team has the knowledge to better understand whether that’s typical of good users or if it’s something they should be concerned about.

Cameron Javier
“Sift tells us so much about our users, thanks to the data across the global network. It picks up on things we may not have thought to look into on our own – those insights are extremely valuable.”

Results

Saving money, saving time

Since implementing Sift, DoorDash is preventing thousands of dollars a day in fraud losses. The Risk team is also faster and more efficient; without Sift, each person could only review a handful of cases a day, but with Sift they’ve increased their efficiency 2x-3x. DoorDash is making more informed decisions, thanks to the shared intelligence of the global network, and as a result they’re ensuring their platform is a safe place for Dashers, merchants, and customers.